1<html> 2<head> 3 <meta charset="utf-8"> 4 <title>Richard Zhang - Research Scientist, Adobe Research</title> 5 <style> 6 .award-icon { 7 position: relative; 8 display: inline-block; 9 } 10 .award-icon img { 11 height: 0.9em; 12 width: auto; 13 vertical-align: -0.1em; 14 } 15 .award-icon:hover::after { 16 content: attr(data-tooltip); 17 position: absolute; 18 bottom: 125%; 19 left: 50%; 20 transform: translateX(-50%); 21 background: #333; 22 color: #fff; 23 padding: 2px 6px; 24 border-radius: 3px; 25 font-size: 9pt; 26 white-space: nowrap; 27 z-index: 10; 28 } 29 </style> 30</head> 31<body> 32<table border="0" width="1100px" align="center"><tbody><tr><td></td><td valign="top"> 33 <br> 34 <table style="font-size: 11pt;" border="0" width="100%"> 35 <tbody><tr> 36 <td width="50%"> 37 <!-- <img width="300" src="./index_files/mypic.jpeg" border="0"> --> 38 <!-- <img width="300" src="./index_files/mypic2.jpg" border="0"> --> 39 <!-- <img width="250" src="./index_files/mypic3.jpg" border="0"> --> 40 <img width="250" src="./index_files/mypic4.jpg" border="0"> 41 </td> 42 <td> 43 <font face="helvetica , ariel, 'sans serif'" size="6"> 44 <b>Richard Zhang</b><br><br> 45 </font> 46 <font face="helvetica , ariel, 'sans serif'" size="4"> 47 Principal Scientist<br> 48 Adobe Research<br> 49 San Francisco, CA<br><br> 50 rizhang@<span class="award-icon" data-tooltip="adobe"><img src="index_files/adobe_logo.png" alt="adobe"></span>.com<br> 51 [<a href="https://github.com/richzhang" border="0">GitHub</a>] 52 [<a href="https://scholar.google.com/citations?user=LW8ze_UAAAAJ&hl=en" border="0">Google Scholar</a>]<br> 53 [<a href="index_files/CV.pdf" border="0">Resume/CV</a>] 54 [<a href="https://twitter.com/rzhang88" border="0">Twitter</a>] 55 [<a href="bio.txt" border="0">Bio</a>]<br> 56 </font> 57 </td> 58 </tr> 59 </tbody></table> 60 <p> 61 </p><hr size="2" align="left" noshade=""> 62 <p> 63 64 <font face="helvetica, ariel, 'sans serif'"> 65 <!--</font></p><h2><font face="helvetica, ariel, 'sans serif'">About Me</font></h2><font face="helvetica, ariel, 'sans serif'">--> 66 My research interests are in computer vision, machine learning, deep learning, graphics, and image processing. I obtained a PhD at UC Berkeley, advised by Prof. <a href="https://people.eecs.berkeley.edu/~efros/">Alexei (Alyosha) Efros</a>. I obtained BS and MEng degrees from Cornell University in ECE. I often collaborate with academic researchers, either through internships or university collaboration.<br><br> 67 68 <!-- <br><br> --> 69 </p><hr size="2" align="left" noshade=""> 70 71 <h3>News </h3> 72 <font face="helvetica, ariel, 'sans serif'"> 73 <span style="font-size: 10pt;"> 74<!-- <b>[Sept 2023]</b> I was included on a list of <a href="https://www.technologyreview.com/innovator/richard-zhang/">35 Innovators Under 35</a> by MIT Technology Review! Please see <a href="https://blog.adobe.com/en/publish/2023/09/12/adobe-research-scientist-named-top-innovator-under-35-mit-technology-review">this article</a> by Adobe and <a href="https://www.youtube.com/watch?v=YQW32sf9noE">this 5 min overview video</a> for more information.<br> --> 75 <!-- <b>[Nov 2023]</b> I appeared on the <a href="https://twimlai.com/podcast/twimlai/visual-generative-ai-ecosystem-challenges/">TWiML podcast</a>, discussing building a healthy GenAI ecosystem for creators, consumers, and contributors. Links: <a href="https://open.spotify.com/episode/6V8zgyf9f6Q6p7rdRhrbpU?si=6670478bdffd46b5">Spotify</a>, <a href="https://podcasts.apple.com/us/podcast/visual-generative-ai-ecosystem-challenges-with-richard/id1116303051?i=1000635452895">Apple</a>, <a href="https://dcs.megaphone.fm/MLN6292733087.mp3">File</a> (40 min); <a href="https://www.youtube.com/watch?v=PdHmoqS70r0">YouTube</a> (51 min).<br> --> 76 <b>[Sept 2026]</b> TPIPS, UNITE, and RAEv2 were accepted to NeurIPS 2026.<br> 77 <b>[Sept 2026]</b> I'll be speaking at the <a href="https://ilr-workshop.github.io/ECCVW2026/">Instance-Level Recognition and Generation (ILR+G)</a> workshop at ECCV 2026.<br> 78 <b>[Jul 2026]</b> I'll be speaking at the <a href="https://fromhv2mv.github.io/">From Human Vision to Machine Vision</a> workshop at SIGGRAPH 2026.<br> 79 <b>[Feb 2026]</b> ID-Sim, Self-Eval, Group Diffusion were accepted to CVPR 2026.<br> 80 <b>[Jan 2026]</b> MotionStream, REPA-E, and NP-Edit were accepted to ICLR 2026.<br> 81 <b>[Jun 2025]</b> Long-Context video models and SliderSpace were accepted to ICCV 2025.<br> 82 <b>[Feb 2025]</b> CausVid and VideoGigaGAN were accepted to CVPR 2025.<br> 83 <b>[Sept 2024]</b> Attribution by Unlearning and DMDv2 were accepted to NeurIPS 2024.<br> 84 <!-- <b>[Aug 2024]</b> Check out TurboEdit, accepted to ECCV 2024.<br> --> 85 <!-- <b>[Jul 2024]</b> Diffusion2GAN, Lazy Diffusion, and Editable Image Elements were accepted to ECCV 2024.<br> --> 86 <!-- <b>[Apr 2024]</b> I'll be speaking at <a href="https://gamgc.github.io/">GenAI Media Challenge</a> and <a href="https://fadetrcv.github.io/2024/">Fair, Data-Efficient, and Trusted Computer Vision</a> workshops.<br> --> 87 <!-- <b>[Feb 2024]</b> DMD was accepted to CVPR 2024.<br> --> 88 <!-- <b>[Sept 2023]</b> DreamSim was accepted to NeurIPS 2023 as a spotlight.<br> --> 89 <!-- <b>[Sept 2023]</b> I was included on MIT Technology Review's list of <a href="https://www.technologyreview.com/innovator/richard-zhang/">35 Innovators Under 35</a>.<br> --> 90 <!-- <b>[Jul 2023]</b> Data Attribution and Concept Ablation were accepted to ICCV 2023.<br> --> 91 <!-- <b>[Jun 2023]</b> Pix2Pix-0 was accepted to SIGGRAPH 2023.<br> --> 92 <!-- <b>[Mar 2023]</b> GigaGAN was selected as a highlight for CVPR 2023.<br> --> 93 <!-- <b>[Feb 2023]</b> GigaGAN, Custom Diffusion, and Domain Expansion were accepted to CVPR 2023.<br> --> 94 <!-- <b>[Oct 2022]</b> I am presenting some posters at ECCV. BlobGAN on Tue, Oct 25, 1100-1330, 3D-FM GAN at 1530-1730, and Anyres-GAN on Wed, Oct 26, 1100-1330. See you there!<br> --> 95 <!-- <b>[Oct 2022]</b> I am co-organizing the <a href="https://she-workshop.github.io/">Sketching for Human Expressivity Workshop</a> at ECCV on Sun, Oct 23rd. See you there!<br> --> 96 <!-- <b>[Sept 2022]</b> ç·ç·å¥½ð<br> --> 97 <!-- <b>[Jul 2022]</b> Any-Resolution GANs, BlobGAN, and 3D-FM GAN were accepted to ECCV 2022.<br> --> 98 <!-- <b>[Jun 2022]</b> Our GANgealing work was one of the 33 best paper finalists at CVPR 2022.<br> --> 99 <!-- <b>[Jun 2022]</b> I spoke about "Anycost and Anyres GANs for Image Synthesis" at the <a href="https://data.vision.ee.ethz.ch/cvl/ntire22/">NTIRE</a> and <a href="https://ai4cc.net/">AICC</a> CVPR 2022 workshops.<br> --> 100 <!-- <b>[May 2022]</b> Please see our SIGGRAPH 2022 work, ASSET, which enables high-resolution semantic editing with transformers.<br> --> 101 <!-- <b>[Apr 2022]</b> Our work on GANgealing was covered by <a href="https://www.youtube.com/watch?v=qtOkktTNs-k">2-minute papers</a>.<br> --> 102 <!-- <b>[Mar 2022]</b> Our works on GANgealing and Vision-Aided GANs were accepted to CVPR as oral presentations.<br> --> 103 <!-- <b>[Mar 2022]</b> Our clean-fid work was accepted to CVPR. <mark><font face="Courier">pip install clean-fid</font></mark> to try it out!<br> --> 104 <!-- <b>[Oct 2021]</b> See Landscape mixer in Photoshop Neural Filters, based on our Swapping Autoencoder work.<br> --> 105 <!-- <b>[July 2021]</b> Our work on editing NeRFs was accepted to ICCV.<br> --> 106 <!-- <b>[Apr 2021]</b> Our work on using generative models to improve discriminative models was accepted to CVPR.<br> --> 107 <!-- <b>[Apr 2021]</b> Our work on few-shot GAN training was accepted to CVPR.<br> --> 108 <!-- <b>[Mar 2021]</b> Our works on speeding up unconditional GANs for image editing and projection (AnyCost GANs) and conditional GANs with implicit functions (ASAPnet) were accepted to CVPR.<br> --> 109 <!-- <b>[Mar 2021]</b> Our work on audio perceptual metrics was accepted to ICASSP.<br> --> 110 <!-- <b>[Sept 2020]</b> Few updates regarding <a href="https://richzhang.github.io/antialiased-cnns/">Antialiasing CNNs</a> [ICML 2019], which can <b>stabilize and improve the backbone for your application</b>:<br> 111 - Easy installation: <mark><font face="Courier">pip install antialiased-cnns</font></mark> and 112 <mark><font face="Courier" color="red">import</font> 113 <font face="Courier">antialiased_cnns; model</font> 114 <font face="Courier" color="blue"> = </font> 115 <font face="Courier">antialiased_cnns.</font><font face="Courier" color="#6c53b5">resnet50</font><font face="Courier">(pretrained=</font> 116 <font face="Courier" color="blue">True)</font></mark><br> 117 - For more information, including "What is Aliasing?", see my <a href="https://youtu.be/8CXrplBG-SE?t=1049">guest lecture</a> [15 min] in SFU CMPT 361, Intro to Vision, Sampling and Aliasing lecture.<br> 118 - A nice followup work, 119 <a href="https://maureenzou.github.io/ddac/">Delving Deeper into Antialiasing in Convnets</a> by Zou, Xiao, Yu, & Lee, won best paper at BMVC 2020. Check it out!<br> --> 120 <!-- <b>[Aug 2020]</b> I gave a talk on <a href="https://www.youtube.com/watch?v=CYdYWeTE-CI">
120Detecting Generated Imagery, Deep and Shallow</a> (35 min) at the <a href="https://sense-human.github.io/">Sensing Humans</a> workshop at ECCV.<br> --> 121 <!-- <b>[Aug 2020]</b> I gave a talk on <a href="https://www.youtube.com/watch?v=aM86tOniH90">Style and Structure Disentanglement for Image Manipulation</a> (30 min) at the <a href="https://data.vision.ee.ethz.ch/cvl/aim20/">Advances in Image Manipulation</a> workshop at ECCV.<br> --> 122 <!-- <b>[Aug 2020]</b> I gave a talk on <a href="https://www.bilibili.com/video/BV1e7411c7kR?p=46">Analyzing Artifacts in Discriminative and Generative Models</a> (40 min) at the GAMES webinar.<br> --> 123 <!-- <b>[July 2020]</b> Our work on using contrastive learning for unpaired translation was accepted to ECCV.<br> --> 124 <!-- <b>[July 2020]</b> Our work on inverting GANs was accepted to ECCV as an oral.<br> --> 125 <!-- <b>[July 2020]</b> See our new work on Swapping Autoencoders below.<br> --> 126 <!-- <b>[July 2020]</b> Our work on audio perceptual metrics was accepted to Intespeech.<br> --> 127 <!-- <b>[Feb 2020]</b> I served as an Area Chair for CVPR 2020 and spoke on <a href="https://www.youtube.com/watch?v=aNDwHRxWTa0">Analyzing CNN Artifacts in Discriminative and Generative Models</a> (11 min). The second half includes our "Detecting CNN-generated images" work, just accepted to CVPR.<br> --> 128 <!-- <b>[Dec 2019]</b> See our new work on detecting CNN-generated images below.<br> --> 129 <!-- <b>[Nov 2019]</b> I presented our "Detecting Photoshop" ICCV19 work at <a href="https://www.youtube.com/watch?v=21lj8tCSMkg">Adobe MAX</a> (5 min), on stage with John Mulaney (aka Peter Porker/Spider-Ham)!<br> --> 130 <!-- <b>[Oct 2019]</b> Thank you <a href="https://twitter.com/Oxford_VGG/status/1184087868857290752">Oxford</a> and UCL for hosting me.<br> --> 131 <!-- <b>[Oct 2019]</b> This <a href="http://video.tv.adobe.com/v/28291">video</a> shows interactive colorization in Photoshop Elements 2020, based on our SIGGRAPH 2017 work.<br> --> 132 <!-- <b>[Sept 2019]</b> See our new work on interactive sketch to image synthesis below.<br> --> 133 <!-- <b>[Jun 2019]</b> See our new work on detecting Photoshopped images below.<br> --> 134 <!-- <b>[May 2019]</b> Our work on anti-aliasing convolutional networks has been accepted to ICML 2019. Try anti-ali
134asing your convnet <a href="https://github.com/adobe/antialiased-cnns">here</a>!<br> --> 135 <!-- <b>[Aug 2018]</b> I will be presenting at the Thesis Fast Forward session at SIGGRAPH on Tuesday 8/14, 2:00pm.<br> --> 136 <!-- <b>[Jun 2018]</b> We will be presenting our <a href="https://richzhang.github.io/PerceptualSimilarity/">project</a> on perceptual metrics at CVPR, Tuesday 6/19, 10:10am. Try our metric <a href="https://github.com/richzhang/PerceptualSimilarity">here</a>!<br> --> 137 <!-- <b>[May 2018]</b> I have <a href="./index_files/graduation.jpg">graduated</a> from UC Berkeley and have joined Adobe Research as a Research Scientist in San Francisco! --> 138 </span> 139 140<!-- </p><hr size="2" align="left" noshade=""> 141 142 <h3>Internship </h3> 143 <font face="helvetica, ariel, 'sans serif'"> 144 <span style="font-size: 10pt;"> 145 If you have similar interests and are interested in collaborating during a Summer 2023 internship, I'd be happy to hear from you! <b>Please apply <a href="https://research.adobe.com/careers/internships/">here</a> first</b>. Tell me about your past research experience and what you would potentially like to do. The goal of an internship is a publication, usually CVPR or SIGGRAPH. Interns are typically PhD students; the number of slots is limited, so we unfortunately cannot accept everyone. 146 </span> 147 </font> 148 --> 149 </p><hr size="2" align="left" noshade=""> 150 151 <h2>Publications </h2> 152 <font face="helvetica, ariel, 'sans serif'"> 153 <table cellspacing="15"> 154 <tbody> 155 <tr> 156 <td width="30%" align=center> 157 <img width="225" align="center" src="https://raw.githubusercontent.com/adobe-research/TPIPS/main/images/teaser.gif" border="0"> 158 </td> 159 <td> 160 <span style="font-size: 12pt;"> 161 <b>The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric</b><br> 162 <span style="font-size: 10pt;"> 163 <a href="https://peterwang512.github.io/">Sheng-Yu Wang</a>, 164 <a href="https://yotamnitzan.github.io/">Yotam Nitzan</a>, 165 <a href="https://www.dgp.toronto.edu/~hertzman/">Aaron Hertzmann</a>, 166 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 167 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 168 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, 169 Richard Zhang 170 <br> 171 To appear in NeurIPS, 2026. <br> 172 [<a href="https://arxiv.org/abs/2607.18237">Paper</a>] 173 [<a href="https://peterwang512.github.io/TPIPS/">Webpage</a>] 174 [<a href="https://github.com/adobe-research/TPIPS">Code</a>] 175 [<a href="https://peterwang512.github.io/TPIPS/#bibtex">Bibtex</a>] 176 <br> 177 </td> 178 </tr> 179 <tr> 180 <td width="30%" align=center> 181 <img width="110" align="center" src="https://raev2.github.io/assets/fig1a_rfid_gfid.png" border="0"> 182 <img width="110" align="center" src="https://raev2.github.io/assets/fig_raev2_gfid_convergence_cfg.png" border="0"> 183 </td> 184 <td> 185 <span style="font-size: 12pt;"> 186 <b>Improved Baselines with Representation Autoencoders</b><br> 187 <span style="font-size: 10pt;"> 188 <a href="https://1jsingh.github.io/">Jaskirat Singh</a>, 189 <a href="https://bytetriper.github.io/">Boyang Zheng</a>, 190 <a href="https://www.zongzewu.com/">Zongze Wu</a>, 191 Richard Zhang, 192 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 193 <a href="https://www.sainingxie.com/">Saining Xie</a> 194 <br> 195 To appear in NeurIPS, 2026. <br> 196 [<a href="https://arxiv.org/abs/2605.18324">Paper</a>] 197 [<a href="https://raev2.github.io/">Webpage</a>] 198 [<a href="https://github.com/nanovisionx/RAEv2">
198Code</a>] 199 [<a href="https://huggingface.co/collections/nyu-visionx/raev2">Models</a>] 200 <br> 201 </td> 202 </tr> 203 <tr> 204 <td width="30%" align=center> 205 <img width="225" align="center" src="https://xingjianbai.com/unite-tokenization-generation/assets/figures/teaser2.png" border="0"> 206 </td> 207 <td> 208 <span style="font-size: 12pt;"> 209 <b>End-to-End Training for Unified Tokenization and Latent Denoising</b><br> 210 <span style="font-size: 10pt;"> 211 <a href="https://shivamduggal4.github.io/">Shivam Duggal</a>, 212 <a href="https://xingjianbai.com/">Xingjian Bai</a>, 213 <a href="https://scholar.google.com/citations?user=V8FwQGkAAAAJ&hl=en">Zongze Wu</a>, 214 Richard Zhang, 215 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 216 <a href="https://groups.csail.mit.edu/vision/torralbalab/">Antonio Torralba</a>, 217 <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, 218 <a href="https://billf.mit.edu/">William T. Freeman</a> 219 <br> 220 To appear in NeurIPS, 2026. <br> 221 [<a href="https://arxiv.org/abs/2603.22283">Paper</a>] 222 [<a href="https://xingjianbai.com/unite-tokenization-generation/">Webpage</a>] 223 [<a href="https://github.com/ShivamDuggal4/UNITE-tokenization-generation/">Code</a>] 224 <br> 225 </td> 226 </tr> 227 <tr> 228 <td width="30%" align=center> 229 <img width="225" align="center" src="https://cfeng16.github.io/on_the_diffusibility/assets/teaser.svg" border="0"> 230 </td> 231 <td> 232 <span style="font-size: 12pt;"> 233 <b>On the Diffusibility of High-Dimensional Latents</b><br> 234 <span style="font-size: 10pt;"> 235 <a href="https://cfeng16.github.io/">Chao Feng</a>, 236 <a href="https://scholar.google.com/citations?user=Qcshi8UAAAAJ&hl=en">Zhiyang Xu</a>, 237 <a href="https://homes.cs.washington.edu/~boweiche/">Bowei Chen</a>, 238 <a href="https://yjxiong.me">Yuanjun Xiong</a>, 239 <a href="https://si0wang.github.io">Xiyao Wang</a>, 240 <a href="https://juiwang.com/">Jui-Hsien Wang</a>, 241 Richard Zhang, 242 <a href="https://sites.google.com/site/zhelin625/">Zhe Lin</a>, 243 <a href="http://andrewowens.com">Andrew Owens</a>, 244 <a href="https://yijunmaverick.github.io/">Yijun Li</a> 245 <br> 246 In ECCV, 2026. <br> 247 [<a href="https://arxiv.org/abs/2609.28473">Paper</a>] 248 [<a href="https://cfeng16.github.io/on_the_diffusibility/">Webpage</a>] 249 <br> 250 </td> 251 </tr> 252 <tr> 253 <td width="30%" align=center> 254 <img width="215" align="center" src="https://juliachae.github.io/id_sim.github.io/static/images/Teaser_Animation.gif" border="0"> 255 </td> 256 <td> 257 <span style="font-size: 12pt;"> 258 <b>ID-Sim: An Identity-Focused Similarity Metric</b><br> 259 <span style="font-size: 10pt;"> 260 <a href="https://juliachae.github.io/">Julia Chae</a>, 261 <a href="https://home.ttic.edu/~nickkolkin/home.html">Nicholas Kolkin</a>, 262 <a href="https://juiwang.com/">Jui-Hsien Wang</a>, 263 Richard Zhang, 264 <a href="https://beerys.github.io/">Sara Beery</a>, 265 <a href="https://cusuh.github.io/">Cusuh Ham</a> 266 <br> 267 In CVPR, 2026. <br> 268 [<a href="https://arxiv.org/abs/2604.05039">Paper</a>] 269 [<a href="https://juliachae.github.io/id_sim.github.io/">Webpage</a>] 270 <br> 271 </td> 272 </tr> 273 <tr> 274 <td width="30%" align=center> 275 <img width="225" align="center" src="https://yotamnitzan.github.io/images/selfE.png" border="0"> 276 </td> 277 <td>
278 <span style="font-size: 12pt;"> 279 <b>Self-Evaluation Unlocks Any-Step Text-to-Image Generation</b><br> 280 <span style="font-size: 10pt;"> 281 <a href="https://xinyu-andy.github.io/">Xin Yu</a>, 282 <a href="https://xjqi.github.io/">Xiaojuan Qi</a>, 283 <a href="https://zhengqili.github.io/">Zhengqi Li</a>, 284 <a href="https://kai-46.github.io/website/">Kai Zhang</a>, 285 Richard Zhang, 286 <a href="https://sites.google.com/site/zhelin625/">Zhe Lin</a>, 287 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 288 <a href="https://stevewongv.github.io/">Tianyu Wang</a>, 289 <a href="https://yotamnitzan.github.io/">Yotam Nitzan </a> 290 <br> 291 In CVPR, 2026. <br> 292 [<a href="https://arxiv.org/abs/2512.22374">Paper</a>] 293 [<a href="https://xinyu-andy.github.io/SelfE-project/">Webpage</a>] 294 <br> 295 </td> 296 </tr> 297 <tr> 298 <td width="30%" align=center> 299 <img width="225" align="center" src="https://sichengmo.github.io/GroupDiff/assets/methods.jpg" border="0"> 300 </td> 301 <td> 302 <span style="font-size: 12pt;"> 303 <b>Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration</b> <br> 304 <span style="font-size: 10pt;"> 305 <a href="https://sichengmo.github.io/">Sicheng Mo</a>, 306 <a href="https://thaoshibe.github.io/">Thao Nguyen</a>, 307 Richard Zhang, 308 <a href="https://home.ttic.edu/~nickkolkin/home.html">Nicholas Kolkin</a>, 309 <a href="https://scholar.google.com/citations?user=7uTobWwAAAAJ&hl=en">Siddharth S. Iyer</a>, 310 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 311 <a href="https://krsingh.cs.ucdavis.edu/">Krishna Kumar Singh</a>, 312 <a href="https://pages.cs.wisc.edu/~yongjaelee/">Yong Jae Lee</a>, 313 <a href="https://boleizhou.github.io/">Bolei Zhou</a>, 314 <a href="https://yuheng-li.github.io/">Yuheng Li</a> 315 <br> 316 In CVPR, 2026. <br> 317 [<a href="https://arxiv.org/abs/2512.10954">Paper</a>] 318 [<a href="https://sichengmo.github.io/GroupDiff/">Webpage</a>] 319 <br> 320 </td> 321 </tr> 322 <tr> 323 <td width="30%" align=center> 324 <img width="225" align="center" src="https://yibingwei-1.github.io/images/qare_teaser.png" border="0"> 325 </td> 326 <td> 327 <span style="font-size: 12pt;"> 328 <b>Towards Text-Guided Attribute-Disentangled Multimodal Representation Learning</b><br> 329 <span style="font-size: 10pt;"> 330 <a href="https://yibingwei-1.github.io/">Yibing Wei</a>, 331 <a href="https://sudeepkatakol.github.io/">Sudeep Katakol</a>, 332 <a href="https://ml-research.github.io/people/mbrack/index.html">Manuel Brack</a>, 333 <a href="https://jonneslin.github.io">Jinhong Lin</a>, 334 <a href="https://haoyuebaizju.github.io/">Haoyue Bai</a>, 335 <a href="https://www.linkedin.com/in/yutengli/">Yu-Teng Li</a>, 336 Richard Zhang, 337 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 338 <a href="https://hareesh-ravi.github.io/">Hareesh Ravi</a>, 339 <a href="https://www.linkedin.com/in/kaleajinkya/">Ajinkya Kale</a> 340 <br> 341 In CVPR Findings, 2026. <br> 342 [<a href="https://openaccess.thecvf.com/content/CVPR2026F/papers/Wei_Towards_Text-Guided_Attribute-Disentangled_Multimodal_Representation_Learning_CVPRF_2026_paper.pdf">Paper</a>] 343 [<a href="https://openaccess.thecvf.com/content/CVPR2026F/supplemental/Wei_Towards_Text-Guided_Attribute-Disentangled_CVPRF_2026_supplemental.pdf">Supp</a>] 344 [<a href="https://github.com/yibingwei-1/QARE">Code</a>] 345 [<a href="https://huggingface.co/datasets/sudeepk/QARE-Benc
345h">Dataset</a>] 346 [<a href="/files/QARE_CVPR2026_Poster.pdf">Poster</a>] 347 <br> 348 </td> 349 </tr> 350 <tr> 351 <td width="30%" align=center> 352 <video width="120" class="video lazy" autoplay loop playsinline controls muted> 353 <source src="https://www.xunhuang.me/imgs/ocean-book_compressed.mp4" type="video/mp4"></source></video> 354 <video width="120" class="video lazy" autoplay loop playsinline controls muted> 355 <source src="https://joonghyuk.com/motionstream-web/assets/streaming_demo/elephant_compressed.mp4" type="video/mp4"></source></video> 356 </td> 357 <td> 358 <span style="font-size: 12pt;"> 359 <b>MotionStream: Real-Time Video Generation with Interactive Motion Controls</b> <br> 360 <span style="font-size: 10pt;"> 361 <a href="https://joonghyuk.com/">Joonghyuk Shin</a>, 362 <a href="https://zhengqili.github.io/">Zhengqi Li</a>, 363 Richard Zhang, 364 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 365 <a href="https://jaesik.info/">Jaesik Park</a>, 366 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 367 <a href="https://www.xunhuang.me/">Xun Huang</a> 368 <br> 369 In ICLR (oral), 2026. <br> 370 [<a href="https://arxiv.org/abs/2511.01266">Paper</a>] 371 [<a href="https://joonghyuk.com/motionstream-web/">Webpage</a>] 372 <br> 373 </td> 374 </tr> 375 <tr> 376 <td width="30%" align=center> 377 <img width="175" align="center" src="https://end2end-diffusion.github.io/irepa/irepa-v2.png" border="0"> 378 </td> 379 <td> 380 <span style="font-size: 12pt;"> 381 <b>What matters for Representation Alignment: Global Information or Spatial Structure?</b> <br> 382 <span style="font-size: 10pt;"> 383 <a href="https://1jsingh.github.io/">Jaskirat Singh</a>, 384 <a href="https://scholar.google.com.au/citations?user=GQzvqS4AAAAJ">Xingjian Leng</a>, 385 <a href="https://betterze.github.io/website/">Zongze Wu</a>, 386 <a href="https://zheng-lab-anu.github.io/">Liang Zheng</a>, 387 Richard Zhang, 388 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 389 <a href="https://www.sainingxie.com/">Saining Xie</a>, 390 <br> 391 In ICLR, 2026. <br> 392 [<a href="https://arxiv.org/abs/2512.10794">Paper</a>] 393 [<a href="https://end2end-diffusion.github.io/irepa/">Webpage</a>] 394 [<a href="https://github.com/end2end-diffusion/irepa">Code</a>] 395 <br> 396 </td> 397 </tr> 398 <tr> 399 <td width="30%" align=center> 400 <img width="175" align="center" src="https://nupurkmr9.github.io/img/npedit_gif.gif" border="0"> 401 </td> 402 <td> 403 <span style="font-size: 12pt;"> 404 <b>NP-Edit: Learning an Image Editing Model without Image Editing Pairs</b> <br> 405 <span style="font-size: 10pt;"> 406 <a href="https://nupurkmr9.github.io/">Nupur Kumari, </a> 407 <a href="https://peterwang512.github.io/">Sheng-Yu Wang, </a> 408 <a href="https://www.nxzhao.com/">Nanxuan Zhao, </a> 409 <a href="https://yotamnitzan.github.io/">Yotam Nitzan, </a> 410 <a href="https://yuheng-li.github.io/">Yuheng Li, </a> 411 <a href="https://krsingh.cs.ucdavis.edu/">Krishna Kumar Singh, </a> 412 Richard Zhang, 413 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman, </a> 414 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu, </a> 415 <a href="https://www.xunhuang.me/">Xun Huang</a> 416 <br> 417 In ICLR, 2026. <br> 418 [<a href="https://arxiv.org/abs/2510.14978">Paper</a>] 419 [<a href="https://nupurkmr9.github.io/npedit/">Webpage</a>] 420 <br> 421 </td> 422 </tr> 423 <tr> 424 <td width="30%" align=center> 425 <img width="225" align="center" src="https://danielchyeh.github.io/x-planner/static/images/figure_overview.png" border="0"> 426 </td> 427 <td>
428 <span style="font-size: 12pt;"> 429 <b>Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing</b><br> 430 <span style="font-size: 10pt;"> 431 <a href="https://danielchyeh.github.io/">Chun-Hsiao Yeh</a>, 432 <a href="https://yilinwang.org/">Yilin Wang</a>, 433 <a href="https://www.nxzhao.com/">Nanxuan Zhao</a>, 434 Richard Zhang, 435 <a href="https://yuheng-li.github.io/">Yuheng Li</a>, 436 <a href="https://people.eecs.berkeley.edu/~yima/">Yi Ma</a>, 437 <a href="https://krsingh.cs.ucdavis.edu/">Krishna Kumar Singh</a> 438 <br> 439 In AAAI, 2026. <br> 440 [<a href="https://arxiv.org/abs/2507.05259">Paper</a>] 441 [<a href="https://danielchyeh.github.io/x-planner/">Webpage</a>] 442 <br> 443 </td> 444 </tr> 445 <tr> 446 <td width="30%" align=center> 447 <img width="175" align="center" src="https://peterwang512.github.io/index_files/fastgda.jpg" border="0"> 448 </td> 449 <td> 450 <span style="font-size: 12pt;"> 451 <b>Fast Data Attribution for Text-to-Image Models</b> <br> 452 <span style="font-size: 10pt;"> 453 <a href="https://peterwang512.github.io">Sheng-Yu Wang</a>, 454 <a href="https://www.dgp.toronto.edu/~hertzman/">Aaron Hertzmann</a>, 455 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, 456 Richard Zhang, 457 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a> 458 <br> 459 In NeurIPS, 2025. <br> 460 [<a href="https://arxiv.org/abs/2511.10721">Paper</a>] 461 [<a href="https://peterwang512.github.io/FastGDA/">Webpage</a>] 462 <br> 463 </td> 464 </tr> 465 <tr> 466 <td width="30%" align=center> 467 <img width="175" align="center" src="https://ryanpo.com/images/ssm_wm.gif" border="0"> 468 </td> 469 <td> 470 <span style="font-size: 12pt;"> 471 <b>Long-Context State-Space Video World Models</b> <br> 472 <span style="font-size: 10pt;"> 473 <a href="https://ryanpo.com/">Ryan Po</a>, 474 <a href="https://yotamnitzan.github.io/">Yotam Nitzan</a>, 475 Richard Zhang, 476 <a href="https://scholar.google.com/citations?user=GkCmZ18AAAAJ&hl=en">Berlin Chen</a>, 477 <a href="https://tridao.me/">Tri Dao</a>, 478 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 479 <a href="https://stanford.edu/~gordonwz/">Gordon Wetzstein</a>, 480 <a href="https://www.xunhuang.me/">Xun Huang</a> 481 <br> 482 In ICCV, 2025. <br> 483 [<a href="https://www.arxiv.org/abs/2505.20171">Paper</a>] 484 [<a href="https://ryanpo.com/ssm_wm/">Webpage</a>] 485 <br> 486 </td> 487 </tr> 488 <tr> 489 <td width="30%" align=center> 490 <img width="100" align="center" src="https://sliderspace.baulab.info/website_gifs/twitter_spaceship.gif" border="0"> 491 <img width="100" align="center" src="https://sliderspace.baulab.info/website_gifs/twitter_monster.gif" border="0"> 492 </td> 493 <td> 494 <span style="font-size: 12pt;"> 495 <b>
495SliderSpace: Decomposing the Visual Capabilities of Diffusion Models</b> <br> 496 <span style="font-size: 10pt;"> 497 <a href="https://rohitgandikota.github.io/">Rohit Gandikota</a>, 498 <a href="https://scholar.google.com/citations?user=V8FwQGkAAAAJ&hl=en">Zongze Wu</a>, 499 Richard Zhang, 500 <a href="https://baulab.info/">David Bau</a>, 501 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 502 <a href="https://home.ttic.edu/~nickkolkin/home.html">Nick Kolkin</a> 503 <br> 504 In ICCV, 2025. <br> 505 [<a href="https://arxiv.org/abs/2412.07772">Paper</a>] 506 [<a href="https://sliderspace.baulab.info/">Webpage</a>] 507 [<a href="https://github.com/rohitgandikota/sliderspace">GitHub</a>] 508 [<a href="https://huggingface.co/spaces/baulab/SliderSpace">Demo</a>] 509 <br> 510 </td> 511 </tr> 512 <tr> 513 <td width="30%" align=center> 514 <video width="120" class="video lazy" autoplay loop playsinline controls muted> 515 <source src="https://huggingface.co/datasets/tianweiy/causvid_website/resolve/main/videos/long_videos/60s/0024.mp4" type="video/mp4"></source></video> 516 <video width="120" class="video lazy" autoplay loop playsinline controls muted> 517 <source src="https://huggingface.co/datasets/tianweiy/causvid_website/resolve/main/videos/i2v/0007.mp4" type="video/mp4"></source></video> 518 </td> 519 <td> 520 <span style="font-size: 12pt;"> 521 <b>From Slow Bidirectional to Fast Causal Video Generators</b> <br> 522 <span style="font-size: 10pt;"> 523 <a href="https://tianweiy.github.io/">Tianwei Yin</a>, 524 <a href="https://www.linkedin.com/in/qiang-zhang-6b48791a7/">Qiang Zhang</a>, 525 Richard Zhang, 526 <a href="https://billf.mit.edu/">William T. Freeman</a>, 527 <a href="https://people.csail.mit.edu/fredo/">Fredo Durand</a>, 528 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 529 <a href="https://www.xunhuang.me/">Xun Huang</a> 530 <br> 531 In CVPR, 2025. <br> 532 [<a href="https://arxiv.org/abs/2412.07772">Paper</a>] 533 [<a href="https://causvid.github.io/">Webpage</a>] 534 <br> 535 </td> 536 </tr> 537 <tr> 538 <td width="30%" align=center> 539 <img width="175" align="center" src="https://twizwei.github.io/assets/images/videogigagan_teaser.gif" border="0"> 540 </td> 541 <td> 542 <span style="font-size: 12pt;"> 543 <b>VideoGigaGAN: Towards Detail-rich Video Super-Resolution</b><br> 544 <span style="font-size: 10pt;"> 545 <a href="https://twizwei.github.io/">Yiran Xu</a>, 546 <a href="https://taesung.me/">Taesung Park</a>, 547 Richard Zhang, 548 <a href="https://research.adobe.com/person/yang-zhou/">Yang Zhou</a>, 549 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 550 <a href="https://pages.cs.wisc.edu/~fliu/">Feng Liu</a>, 551 <a href="https://jbhuang0604.github.io/">Jia-Bin Huang</a>, 552 <a href="https://difanliu.github.io/">Difan Liu</a> 553 <br> 554 In CVPR, 2025. <br> 555 [<a href="https://arxiv.org/abs/2404.12388">Paper</a>] 556 [<a href="https://videogigagan.github.io/">Webpage</a>] 557 [<a href="https://videogigagan.github.io/#BibTeX">Bibtex</a>] 558 <br> 559 </td> 560 </tr> 561 <tr> 562 <td width="30%" align=center> 563 <img width="200" align="center" src="https://netanel-tamir.github.io/assets/img/publication_preview/isqoe.png" border="0"> 564 </td> 565 <td>
566 <span style="font-size: 12pt;"> 567 <b>What Makes for a Good Stereoscopic Image?</b><br> 568 <span style="font-size: 10pt;"> 569 <a href="https://netanel-tamir.github.io">Netanel Y. Tamir</a>, 570 <a href="https://www.linkedin.com/in/shiramir/">Shir Amir</a>, 571 <a href="https://www.linkedin.com/in/ranel-itzhaky-847070254/">Ranel Itzhaky</a>, 572 <a href="https://www.linkedin.com/in/noam-atia/">Noam Atia</a>, 573 <a href="https://ssundaram21.github.io/">Shobhita Sundaram</a>, 574 <a href="https://stephanie-fu.github.io/">Stephanie Fu</a>, 575 <a href="https://www.linkedin.com/in/ronus/">Ron Sokolovsky</a>, 576 <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, 577 <a href="https://www.weizmann.ac.il/math/dekel/home">Tali Dekel</a>, 578 Richard Zhang, 579 <a href="https://www.linkedin.com/in/miriam-farber-1a07bb145/">Miriam Farber</a> 580 <br> 581 In CVPR CV4Metaverse Workshop, 2025. <br> 582 [<a href="https://arxiv.org/abs/2412.21127">Paper</a>] 583 [<a href="https://github.com/apple/ml-isqoe">GitHub</a>] 584 [<a href="https://github.com/apple/ml-isqoe?tab=readme-ov-file#citation">Bibtex</a>] 585 <br> 586 </td> 587 </tr> 588 <tr> 589 <td width="30%" align=center> 590 <img width="200" align="center" src="https://peterwang512.github.io/AttributeByUnlearning/files/teaser.jpg" border="0"> 591 </td> 592 <td> 593 <span style="font-size: 12pt;"> 594 <b>Data Attribution for Text-to-Image Models by Unlearning Synthesized Images</b> <br> 595 <span style="font-size: 10pt;"> 596 <a href="https://peterwang512.github.io">Sheng-Yu Wang</a>, 597 <a href="https://www.dgp.toronto.edu/~hertzman/">Aaron Hertzmann</a>, 598 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, 599 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 600 Richard Zhang 601 <br> 602 In NeurIPS, 2024. <br> 603 [<a href="https://arxiv.org/abs/2406.09408">Paper</a>] 604 [<a href="https://peterwang512.github.io/AttributeByUnlearning/">Webpage</a>] 605 <br> 606 </td> 607 </tr> 608 <tr> 609 <td width="30%" align=center> 610 <img width="250" align="center" src="https://tianweiy.github.io/dmd2/static/images/pipeline.jpg" border="0"> 611 </td> 612 <td> 613 <span style="font-size: 12pt;"> 614 <b>Improved Distribution Matching Distillation for Fast Image Synthesis</b> <br> 615 <span style="font-size: 10pt;"> 616 <a href="https://tianweiy.github.io/">Tianwei Yin</a>, 617 <a href="http://mgharbi.com/">Michael Gharbi</a>, 618 <a href="https://taesung.me/">Taesung Park</a>, 619 Richard Zhang, 620 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 621 <a href="https://people.csail.mit.edu/fredo/">Fredo Durand</a>, 622 <a href="https://billf.mit.edu/">William T. Freeman</a> 623 <br> 624 In NeurIPS (oral), 2024. <br> 625 [<a href="https://arxiv.org/abs/2405.14867">Paper</a>] 626 [<a href="https://tianweiy.github.io/dmd2/">Webpage</a>] 627 [<a href="https://tianweiy.github.io/dmd2/#bibtex">Bibtex</a>] 628 <br> 629 </td> 630 </tr> 631 <tr> 632 <td width="30%" align=center> 633 <img width="240" align="center" src="index_files/teaser_customdiffusion360.jpeg" border="0"> 634 </td> 635 <td>
636 <span style="font-size: 12pt;"> 637 <b>Customizing Text-to-Image Diffusion with Camera Viewpoint Control</b><br> 638 <span style="font-size: 10pt;"> 639 <a href="https://nupurkmr9.github.io/">Nupur Kumari</a>, 640 <a href="https://graceduansu.github.io/">Grace Su</a>, 641 Richard Zhang, 642 <a href="https://taesung.me/">Taesung Park</a>, 643 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 644 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a> 645 <br> 646 In SIGGRAPH Asia, 2024. <br> 647 [<a href="https://arxiv.org/abs/2404.12333">Paper</a>] 648 [<a href="https://customdiffusion360.github.io/">Webpage</a>] 649 [<a href="https://github.com/customdiffusion360/custom-diffusion360">GitHub</a>] 650 [<a href="https://huggingface.co/spaces/customdiffusion360/customdiffusion360">Demo</a>] 651 <br> 652 </td> 653 </tr> 654 <tr> 655 <td width="30%" align=center> 656 <video width="70" class="video lazy" autoplay loop playsinline controls muted> 657 <source src="https://joaanna.github.io/customizing_motion/static/videos/many/carlton/An_older_lady_doing_the_pnn_dance_while_jumping_up_and_down_._seed49954.mp4" type="video/mp4"></source></video> 658 <video width="70" class="video lazy" autoplay loop playsinline controls muted> 659 <source src="https://joaanna.github.io/customizing_motion/static/videos/many/carlton/nurses_dancing_the_sks_dance_in_a_hospital_seed0.mp4" type="video/mp4"></source></video> 660 <video width="70" class="video lazy" autoplay loop playsinline controls muted> 661 <source src="https://joaanna.github.io/customizing_motion/static/videos/many/carlton/A_toddler_giggling_while_attempting_the_sks_dance_in_the_living_room._seed0.mp4" type="video/mp4"></source> 662 </video> 663 </td> 664 <td> 665 <span style="font-size: 12pt;"> 666 <b>NewMove: Customizing text-to-video models with novel motions</b> <br> 667 <span style="font-size: 10pt;"> 668 <a href="https://joaanna.github.io/">Joanna Materzynska</a>, 669 <a href="http://people.ciirc.cvut.cz/~sivic/">Josef Sivic</a>, 670 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 671 <a href="https://groups.csail.mit.edu/vision/torralbalab/">Antonio Torralba</a>, 672 Richard Zhang, 673 <a href="https://bryanrussell.org/">Bryan Russell</a> 674 <br> 675 In ACCV, 2024. <br> 676 [<a href="https://arxiv.org/abs/2312.04966">Paper</a>] 677 [<a href="https://joaanna.github.io/customizing_motion/">Webpage</a>] 678 [<a href="index_files/bibtex_arxiv23_motioncust.txt">Bibtex</a>] 679 <br> 680 </td> 681 </tr> 682 <tr> 683 <td width="30%" align=center> 684 <img width="75" align="center" src="https://betterze.github.io/TurboEdit/img/black2white.gif" border="0"> 685 <img width="75" align="center" src="https://betterze.github.io/TurboEdit/img/short.gif" border="0"> 686 <img width="75" align="center" src="https://betterze.github.io/TurboEdit/img/pharaoh2fox.gif" border="0"> 687 </td> 688 <td> 689 <span style="font-size: 12pt;"> 690 <b>TurboEdit: Instant text-based image editing</b> <br>
691 <span style="font-size: 10pt;"> 692 <a href="https://scholar.google.com/citations?user=V8FwQGkAAAAJ&hl=en">Zongze Wu</a>, 693 <a href="https://home.ttic.edu/~nickkolkin/home.html">Nicholas Kolkin</a>, 694 <a href="https://www.linkedin.com/in/jonathan-brandt-23b334/">Jonathan Brandt</a>, 695 Richard Zhang, 696 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a> 697 <br> 698 In ECCV, 2024. <br> 699 [<a href="https://arxiv.org/abs/2408.08332">Paper</a>] 700 [<a href="https://betterze.github.io/TurboEdit/">Webpage</a>] 701 <br> 702 </td> 703 </tr> 704 <tr> 705 <td width="30%" align=center> 706 <img width="250" align="center" src="https://mingukkang.github.io/Diffusion2GAN/static/images/G_architecture.png" border="0"> 707 </td> 708 <td> 709 <span style="font-size: 12pt;"> 710 <b>Diffusion2GAN: Distilling Diffusion Models into Conditional GANs</b> <br> 711 <span style="font-size: 10pt;"> 712 <a href="https://mingukkang.github.io/">Minguk Kang</a>, 713 Richard Zhang, 714 <a href="https://www.connellybarnes.com/work/">Connelly Barnes</a>, 715 <a href="https://research.adobe.com/person/sylvain-paris/">Sylvain Paris</a>, 716 <a href="https://suhakwak.github.io/">Suha Kwak</a>, 717 <a href="https://jaesik.info/">Jaesik Park</a>, 718 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 719 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 720 <a href="https://taesung.me/">Taesung Park</a> 721 <br> 722 In ECCV, 2024. <br> 723 [<a href="https://arxiv.org/abs/2405.05967">Paper</a>] 724 [<a href="https://mingukkang.github.io/Diffusion2GAN/">Webpage</a>] 725 [<a href="https://mingukkang.github.io/Diffusion2GAN#bibtex">Bibtex</a>] 726 <br> 727 </td> 728 </tr> 729 <tr> 730 <td width="30%" align=center> 731 <video width="150" class="video lazy" autoplay loop playsinline controls muted> 732 <source src="https://jitengmu.github.io/Editable_Image_Elements/static/images/teaser_combine.mp4" type="video/mp4"></source></video> 733 </td> 734 <td> 735 <span style="font-size: 12pt;"> 736 <b>Editable Image Elements for Controllable Synthesis</b> <br> 737 <span style="font-size: 10pt;"> 738 <a href="https://jitengmu.github.io/">Jiteng Mu</a>, 739 <a href="http://mgharbi.com/">Michael Gharbi</a>, 740 Richard Zhang, 741 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 742 <a href="http://www.svcl.ucsd.edu/~nuno/">Nuno Vasconcelos</a>, 743 <a href="https://xiaolonw.github.io/">Xiaolong Wang</a>, 744 <a href="https://taesung.me/">Taesung Park</a>, 745 <br> 746 In ECCV, 2024. <br> 747 [<a href="https://arxiv.org/abs/2404.16029">Paper</a>] 748 [<a href="https://jitengmu.github.io/Editable_Image_Elements/">Webpage</a>] 749 <br> 750 </td> 751 </tr> 752 <tr> 753 <td width="30%" align=center> 754 <img width="240" align="center" src="https://lazydiffusion.github.io/static/images/teaser.png" border="0"> 755 </td> 756 <td>
757 <span style="font-size: 12pt;"> 758 <b>Lazy Diffusion Transformer for Interactive Image Editing</b><br> 759 <span style="font-size: 10pt;"> 760 <a href="https://yotamnitzan.github.io/">Yotam Nitzan</a>, 761 <a href="https://www.cs.huji.ac.il/w~wuzongze/">Zongze Wu</a>, 762 Richard Zhang, 763 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 764 <a href="https://danielcohenor.com/">Daniel Cohen-Or</a>, 765 <a href="https://taesung.me/">Taesung Park</a>, 766 <a href="http://mgharbi.com/">Michael Gharbi</a> 767 <br> 768 In ECCV, 2024. <br> 769 [<a href="https://arxiv.org/abs/2404.12382">Paper</a>] 770 [<a href="https://lazydiffusion.github.io/">Webpage</a>] 771 <br> 772 </td> 773 </tr> 774 <tr> 775 <td width="30%" align=center> 776 <img width="160" align="center" src="index_files/moe_eccv24_teaser.jpg" border="0"> 777 </td> 778 <td> 779 <span style="font-size: 12pt;"> 780 <b>Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection</b><br> 781 <span style="font-size: 10pt;"> 782 <a href="https://alii-ganjj.github.io/">Alireza Ganjdanesh</a>, 783 <a href="https://research.adobe.com/person/yan-kang/">Yan Kang</a>, 784 <a href="https://lychenyoko.github.io/">Yuchen Liu</a>, 785 Richard Zhang, 786 <a href="https://research.adobe.com/person/zhe-lin/">Zhe Lin</a>, 787 <a href="https://www.cs.umd.edu/people/heng">Heng Huang</a> 788 <br> 789 In ECCV, 2024. <br> 790 [<a href="https://arxiv.org/abs/2409.15557">Paper</a>] 791 <br> 792 </td> 793 </tr> 794 <tr> 795 <td width="30%" align=center> 796 <img width="150" align="center" src="index_files/teaser_dmd.gif" border="0"> 797 </td> 798 <td> 799 <span style="font-size: 12pt;"> 800 <b>One-step Diffusion with Distribution Matching Distillation</b> <br> 801 <span style="font-size: 10pt;"> 802 <a href="https://tianweiy.github.io/">Tianwei Yin</a>, 803 <a href="http://mgharbi.com/">Michael Gharbi</a>, 804 Richard Zhang, 805 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 806 <a href="https://people.csail.mit.edu/fredo/">Fredo Durand</a>, 807 <a href="https://billf.mit.edu/">William T. Freeman</a>, 808 <a href="https://taesung.me/">Taesung Park</a> 809 <br> 810 In CVPR, 2024. <br> 811 [<a href="https://arxiv.org/abs/2311.18828">Paper</a>] 812 [<a href="https://tianweiy.github.io/dmd/">Webpage</a>] 813 [<a href="https://www.youtube.com/watch?v=3vo6mzk9K4s&list=TLGGlJBiJ80Rt-wwMTEyMjAyMw">Teaser</a>] 814 [<a href="index_files/bibtex_dmd2023.txt">Bibtex</a>] 815 <br> 816 </td> 817 </tr> 818 <tr> 819 <td width="30%" align=center> 820 <img width="250" align="center" src="index_files/personalized_res.jpeg" border="0"> 821 </td> 822 <td> 823 <span style="font-size: 12pt;"> 824 <b>Personalized Residuals for Concept-Driven Text-to-Image Generation</b> <br>
825 <span style="font-size: 10pt;"> 826 <a href="https://cusuh.github.io/">Cusuh Ham</a>, 827 <a href="https://techmatt.github.io/">Matthew Fisher</a>, 828 <a href="https://faculty.cc.gatech.edu/~hays/">James Hays</a>, 829 <a href="https://home.ttic.edu/~nickkolkin/home.html">Nick Kolkin</a>, 830 <a href="https://lychenyoko.github.io/">Yuchen Liu</a>, 831 Richard Zhang, 832 <a href="https://www.tobiashinz.com/">Tobias Hinz</a> 833 <br> 834 In CVPR, 2024. <br> 835 [<a href="https://arxiv.org/abs/2405.12978">Paper</a>] 836 [<a href="https://cusuh.github.io/personalized-residuals/">Webpage</a>] 837 [<a href="https://cusuh.github.io/personalized-residuals/resources/bibtex.txt">Bibtex</a>] 838 <br> 839 </td> 840 </tr> 841 <tr> 842 <td width="30%" align=center> 843 <img width="250" align="center" src="https://yinboc.github.io/infd/assets/method.png" border="0"> 844 </td> 845 <td> 846 <span style="font-size: 12pt;"> 847 <b>Image Neural Field Diffusion Models</b> <br> 848 <span style="font-size: 10pt;"> 849 <a href="https://yinboc.github.io/">Yinbo Chen</a>, 850 <a href="https://oliverwang.nfshost.com/">Oliver Wang</a>, 851 Richard Zhang, 852 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 853 <a href="https://xiaolonw.github.io/">Xiaolong Wang</a>, 854 <a href="http://www.mgharbi.com/">Michael Gharbi</a> 855 <br> 856 In CVPR, 2024 (highlight). <br> 857 [<a href="https://arxiv.org/abs/2406.07480">Paper</a>] 858 [<a href="https://yinboc.github.io/infd/">Webpage</a>] 859 <!-- [<a href="https://cusuh.github.io/personalized-residuals/resources/bibtex.txt">Bibtex</a>] --> 860 <br> 861 </td> 862 </tr> 863 <tr> 864 <td width="30%" align=center> 865 <img width="200" align="center" src="https://jeanne-wang.github.io/jumpcutsmoothing/assets/method.jpg" border="0"> 866 </td> 867 <td> 868 <span style="font-size: 12pt;"> 869 <b>Jump Cut Smoothing for Talking Heads</b><br> 870 <span style="font-size: 10pt;"> 871 <a href="https://jeanne-wang.github.io/">Xiaojuan Wang</a>, 872 <a href="https://taesung.me/">Taesung Park</a>, 873 <a href="https://research.adobe.com/person/yang-zhou/">Yang Zhou</a>, 874 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 875 Richard Zhang 876 <br> 877 In ArXiv, 2024. <br> 878 [<a href="https://arxiv.org/abs/2401.04718">Paper</a>] 879 [<a href="https://jeanne-wang.github.io/jumpcutsmoothing/">Webpage</a>] 880 <br> 881 </td> 882 </tr> 883 <tr> 884 <td width="30%" align=center> 885 <img width="225" align="center" src="index_files/teaser_dreamsim.jpg" border="0"> 886 </td> 887 <td> 888 <span style="font-size: 12pt;"> 889 <b>DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data</b> <br> 890 <span style="font-size: 10pt;"> 891 <a href="https://stephanie-fu.github.io/">Stephanie Fu</a>*, 892 <a href="https://netanel-tamir.github.io/">Netanel Tamir</a>*, 893 <a href="https://ssundaram21.github.io/">Shobhita Sundaram</a>*, 894 <a href="http://people.csail.mit.edu/lrchai/">Lucy Chai</a>, 895 Richard Zhang, 896 <a href="http://web.mit.edu/phillipi/">Tali Dekel</a>, 897 <a href="http://web.mit.edu/phillipi/">Phillip Isola</a><br>(*equal contribution) 898 <br> 899 In NeurIPS (spotlight), 2023. <br> 900 [<a href="https://arxiv.org/abs/2306.09344">Paper</a>] 901 [<a href="https://dreamsim-nights.github.io/">Webpage</a>] 902 [<a href="https://github.com/ssundaram21/dreamsim">GitHub</a>] 903 [<a href="https://github.com/ssundaram21/dreamsim#citation">Bibtex</a>] 904 <br> 905 </td> 906 </tr> 907 <tr> 908 <td width="30%" align=center> 909 <img width="250" align="center" src="index_files/datattribution_teaser.jpg" border="0"> 910 </td> 911 <td>
912 <span style="font-size: 12pt;"> 913 <b>Evaluating Data Attribution for Text-to-Image Models</b> <br> 914 <span style="font-size: 10pt;"> 915 <a href="https://peterwang512.github.io">Sheng-Yu Wang</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, Richard Zhang<br> 916 In ICCV, 2023. <br> 917 [<a href="https://arxiv.org/abs/2306.09345">Paper</a>] 918 [<a href="https://peterwang512.github.io/GenDataAttribution/">Webpage</a>] 919 [<a href="https://github.com/peterwang512/GenDataAttribution">GitHub</a>] 920 [<a href="index_files/bibtex_arxiv23_datattribution">Bibtex</a>] 921 <br> 922 </td> 923 </tr> 924 <tr> 925 <td width="30%" align=center> 926 <img width="200" align="center" src="index_files/teaser_ablate.jpeg" border="0"> 927 </td> 928 <td> 929 <span style="font-size: 12pt;"> 930 <b>Ablating Concepts in Text-to-Image Diffusion Models</b> <br> 931 <span style="font-size: 10pt;"> 932 <a href="https://nupurkmr9.github.io/">Nupur Kumari</a>, Bingliang Zhang, <a href="https://peterwang512.github.io">Sheng-Yu Wang</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, Richard Zhang, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 933 In ICCV, 2023. <br> 934 [<a href="https://arxiv.org/abs/2303.13516">Paper</a>] 935 [<a href="https://www.cs.cmu.edu/~concept-ablation/">Webpage</a>] 936 [<a href="https://github.com/nupurkmr9/concept-ablation">GitHub</a>] 937 [<a href="https://github.com/nupurkmr9/concept-ablation#citation">Bibtex</a>] 938 <br> 939 </td> 940 </tr> 941 <tr> 942 <td width="30%" align=center> 943 <img width="250" align="center" src="index_files/onlinegenai.gif" border="0"> 944 </td> 945 <td> 946 <span style="font-size: 12pt;"> 947 <b>Online Detection of AI-Generated Images</b> <br> 948 <span style="font-size: 10pt;"> 949 David C. Epstein, Ishan Jain, <a href="http://www.oliverwang.info/">Oliver Wang</a>, Richard Zhang<br> 950 In ICCV DFAD Workshop, 2023. <br> 951 [<a href="https://arxiv.org/abs/2310.15150">Paper</a>] 952 [<a href="https://richzhang.github.io/OnlineGenAIDetection">Webpage</a>] 953 [<a href="https://www.dropbox.com/scl/fi/31zlp098mmjydde42eu2f/iccv_presentation_genai_detection_FINAL.pptx?rlkey=bt7ibittpv5h6d7n208s1n6bu&dl=0">Slides</a>] 954 [<a href="https://www.dropbox.com/scl/fi/acfydxgdlxss48q3jii2d/iccv_dfad_poster.pdf?rlkey=3fzu1z5jynix3t86enurtd1w3&dl=0">Poster</a>] 955 [<a href="https://richzhang.github.io/OnlineGenAIDetection/resources/bibtex.txt">Bibtex</a>] 956 <br> 957 </td> 958 </tr> 959 <tr> 960 <td width="30%" align=center> 961 <img width="180" align="center" src="https://pix2pixzero.github.io/assets/main_v6.gif" border="0"> 962 </td> 963 <td> 964 <span style="font-size: 12pt;"> 965 <b>Zero-shot Image-to-Image Translation</b> <br> 966 <span style="font-size: 10pt;"> 967 <a href="https://gauravparmar.com/">Gaurav Parmar</a>, 968 <a href="http://krsingh.cs.ucdavis.edu/">Krishna Kumar Singh</a>, 969 Richard Zhang, 970 <a href="https://yijunmaverick.github.io/">Yijun Li</a>, 971 <a href="https://research.adobe.com/person/jingwan-lu/">Jingwan Lu</a>, 972 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 973 In SIGGRAPH, 2023. <br> 974 [<a href="https://arxiv.org/abs/2302.03027">Paper</a>] 975 [<a href="https://pix2pixzero.github.io/">Webpage</a>] 976 [<a href="https://github.com/pix2pixzero/pix2pix-zero">GitHub</a>]
977 [<a href="https://huggingface.co/spaces/pix2pix-zero-library/pix2pix-zero-demo">Demo</a>] 978 <br> 979 </td> 980 </tr> 981 <tr> 982 <td width="30%" align=center> 983 <img width="100" align="center" src="index_files/gigagan_teaser.jpg" border="0"> 984 <img width="126" align="center" src="index_files/gigagan_teaser2.jpg" border="0"> 985 </td> 986 <td> 987 <span style="font-size: 12pt;"> 988 <b>Scaling up GANs for Text-to-Image Synthesis</b> <br> 989 <span style="font-size: 10pt;"> 990 <a href="https://mingukkang.github.io/">Minguk Kang</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, Richard Zhang, <a href="https://jaesik.info/">Jaesik Park</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="https://research.adobe.com/person/sylvain-paris/">Sylvain Paris</a>, <a href="https://taesung.me/">Taesung Park</a><br> 991 In CVPR (highlight), 2023. <br> 992 [<a href="https://arxiv.org/abs/2303.05511">Paper</a>] 993 [<a href="https://mingukkang.github.io/GigaGAN/">Webpage</a>] 994 [<a href="https://mingukkang.github.io/GigaGAN/#bibtex">Bibtex</a>] 995 <br> 996 </td> 997 </tr> 998 <tr> 999 <td width="30%" align=center> 1000 <img width="250" align="center" src="index_files/custom_diffusion_teaser.png" border="0"> 1001 </td> 1002 <td> 1003 <span style="font-size: 12pt;"> 1004 <b>Multi-Concept Customization of Text-to-Image Diffusion</b> <br> 1005 <span style="font-size: 10pt;"> 1006 <a href="https://nupurkmr9.github.io/">Nupur Kumari</a>, Bingliang Zhang, Richard Zhang, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 1007 In CVPR, 2023. <br> 1008 [<a href="https://arxiv.org/abs/2212.04488">Paper</a>] 1009 [<a href="https://www.cs.cmu.edu/~custom-diffusion/">Webpage</a>] 1010 [<a href="https://github.com/adobe-research/custom-diffusion">GitHub</a>] 1011 [<a href="https://github.com/adobe-research/custom-diffusion#references">Bibtex</a>] 1012 <br> 1013 </td> 1014 </tr> 1015 <tr> 1016 <td width="30%" align=center> 1017 <video width="200" class="video lazy" autoplay loop playsinline controls muted> 1018 <source src="https://yotamnitzan.github.io/domain-expansion/assets/videos/teaser_video.mp4" type="video/mp4"></source> 1019 </video> 1020 </td> 1021 <td> 1022 <span style="font-size: 12pt;"> 1023 <b>Domain Expansion of Image Generators</b> <br> 1024 <span style="font-size: 10pt;"> 1025 <a href="https://yotamnitzan.github.io/">Yotam Nitzan</a>, <a href="http://www.mgharbi.com/">Michaël Gharbi</a>, Richard Zhang, <a href="https://taesung.me/">Taesung Park</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="https://danielcohenor.com/">Daniel Cohen-Or</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a><br> 1026 In CVPR, 2023. <br> 1027 [<a href="https://arxiv.org/abs/2301.05225">Paper</a>] 1028 [<a href="https://yotamnitzan.github.io/domain-expansion/">Webpage</a>] 1029 [<a href="https://github.com/adobe-research/domain-expansion">GitHub</a>] 1030 [<a href="https://github.com/adobe-research/domain-expansion#bibtex">Bibtex</a>] 1031 <br> 1032 </td> 1033 </tr> 1034 <tr> 1035 <td width="30%" align=center> 1036 <!-- height="74" --> 1037 <!-- <center> --> 1038 <img width="230" align="center" src="index_files/arxiv21_expandcollapse_teaser.jpg" border="0"> 1039 <!-- </center> --> 1040 </td> 1041 <td>
1042 <span style="font-size: 12pt;"> 1043 <b>The Low-Rank Simplicity Bias in Deep Networks</b> <br> 1044 <span style="font-size: 10pt;"> 1045 <a href="http://people.csail.mit.edu/minhuh/">Minyoung Huh</a>, <a href="https://people.csail.mit.edu/hmobahi/">Hossein Mobahi</a>, Richard Zhang, <a href="https://scholar.google.com/citations?user=7N-ethYAAAAJ&hl=en">Brian Cheung</a>, <a href="https://people.csail.mit.edu/pulkitag/">Pulkit Agrawal</a>, <a href="http://web.mit.edu/phillipi/">Phillip Isola</a><br> 1046 In TMLR, 2023. <br> 1047 [<a href="https://arxiv.org/abs/2103.10427">Paper</a>] 1048 [<a href="https://minyoungg.github.io/overparam">Webpage</a>] 1049 [<a href="https://github.com/minyoungg/overparam">GitHub</a>] 1050 [<a href="https://github.com/minyoungg/overparam#3-cite">Bibtex</a>] 1051 <br> 1052 </td> 1053 </tr> 1054 <tr> 1055 <td width="30%" align=center> 1056 <img width="100" align="center" src="https://github.com/chail/anyres-gan/blob/main/img/github_loop.gif?raw=true" border="0"> 1057 </td> 1058 <td> 1059 <span style="font-size: 12pt;"> 1060 <b>Any-resolution Training for High-resolution Image Synthesis</b> <br> 1061 <span style="font-size: 10pt;"> 1062 <a href="http://people.csail.mit.edu/lrchai/">Lucy Chai</a>, <a href="http://www.mgharbi.com/">Michaël Gharbi</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 1063 <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, Richard Zhang<br> 1064 In ECCV, 2022. <br> 1065 [<a href="https://arxiv.org/abs/2204.07156">Paper</a>] 1066 [<a href="https://chail.github.io/anyres-gan/">Webpage</a>] 1067 [<a href="https://github.com/chail/anyres-gan">GitHub</a>] 1068 [<a href="https://www.youtube.com/watch?v=0l11u2HzQrQ&feature=emb_title&ab_channel=LucyChai">Video</a>] 1069 [<a href="https://chail.github.io/anyres-gan/bibtex.txt">Bibtex</a>] 1070 <br> 1071 </td> 1072 </tr> 1073 <tr> 1074 <td width="30%" align=center> 1075 <!-- <img width="100" align="center" src="https://dave.ml/blobgan/static/vids/moveall_bg.mp4" border="0"> --> 1076 <video src="https://dave.ml/blobgan/static/vids/moveall_bg.mp4" data-no-pause="" autoplay="" playsinline="" muted="" loop="" width=180></video> 1077 </td> 1078 <td> 1079 <span style="font-size: 12pt;"> 1080 <b>BlobGAN: Spatially Disentangled Scene Representations</b> <br> 1081 <span style="font-size: 10pt;"> 1082 <a href="https://dave.ml/">Dave Epstein</a>, <a href="https://taesung.me/">Taesung Park</a>, Richard Zhang, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> 1083 In ECCV, 2022. <br> 1084 [<a href="https://arxiv.org/abs/2205.02837">Paper</a>] 1085 [<a href="https://dave.ml/blobgan/">Webpage</a>] 1086 [<a href="https://github.com/dave-epstein/blobgan">GitHub</a>] 1087 [<a href="https://www.youtube.com/watch?v=KpUv82VsU5k">Video</a>] 1088 [<a href="https://dave.ml/blobgan/#citation">Bibtex</a>] 1089 <br> 1090 </td> 1091 </tr> 1092 <tr> 1093 <td width="30%" align=center> 1094 <img width="200" align="center" src="https://lychenyoko.github.io/3D-FM-GAN-Webpage/resources/Teaser.gif?raw=true" border="0"> 1095 </td> 1096 <td>
1097 <span style="font-size: 12pt;"> 1098 <b>3D-FM GAN: Towards 3D-Controllable Face Manipulation</b> <br> 1099 <span style="font-size: 10pt;"> 1100 <a href="https://lychenyoko.github.io/">Yuchen Liu</a>, 1101 <a href="https://zhixinshu.github.io/">Zhixin Shu</a>, 1102 <a href="https://yijunmaverick.github.io/">Yijun Li</a>, 1103 <a href="https://sites.google.com/site/zhelin625/">Zhe Lin</a>, 1104 Richard Zhang, 1105 <a href="https://ece.princeton.edu/people/sun-yuan-kung">Sun-Yuan Kung</a> <br> 1106 In ECCV, 2022. <br> 1107 [<a href="https://arxiv.org/abs/2208.11257">Paper</a>] 1108 [<a href="https://lychenyoko.github.io/3D-FM-GAN-Webpage/">Webpage</a>] 1109 <!-- [<a href="">GitHub</a>] --> 1110 [<a href="https://www.youtube.com/watch?v=3tR7qIXyzLE">Video</a>] 1111 <!-- [<a href="">Bibtex</a>] --> 1112 <br> 1113 </td> 1114 </tr> 1115 <tr> 1116 <td width="30%" align=center> 1117 <img width="180" align="center" src="https://research.adobe.com/wp-content/uploads/2022/11/Ehn5Gr9BdAgzEF1o.jpg" border="0"> 1118 </td> 1119 <td> 1120 <span style="font-size: 12pt;"> 1121 <b>ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions</b> <br> 1122 <span style="font-size: 10pt;"> 1123 <a href="https://people.cs.umass.edu/~dliu/">Difan Liu</a>, Sandesh Shetty, <a href="http://www.tobiashinz.com/">Tobias Hinz</a>, <a href="https://techmatt.github.io/">Matthew Fisher</a>, Richard Zhang, <a href="https://taesung.me/">Taesung Park</a>, <a href="https://people.cs.umass.edu/~kalo/">Evangelos Kalogerakis</a><br> 1124 In SIGGRAPH, 2022. <br> 1125 [<a href="https://arxiv.org/abs/2205.12231">Paper</a>] 1126 [<a href="https://people.cs.umass.edu/~dliu/projects/ASSET/">Webpage</a>] 1127 [<a href="https://github.com/DifanLiu/ASSET">GitHub</a>] 1128 [<a href="https://people.cs.umass.edu/~dliu/projects/ASSET/resources/bibtex.txt">Bibtex</a>] 1129 <br> 1130 </td> 1131 </tr> 1132 1133 <tr> 1134 <td width="30%" align=center> 1135 <img width="230" align="center" src="index_files/cats_cube_3.gif" border="0"> 1136 </td> 1137 <td> 1138 <span style="font-size: 12pt;"> 1139 <b>GAN-Supervised Dense Visual Alignment</b> <br> 1140 <span style="font-size: 10pt;"> 1141 <a href="https://www.wpeebles.com/">William Peebles</a>, 1142 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 1143 Richard Zhang, 1144 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, 1145 <a href="https://groups.csail.mit.edu/vision/torralbalab/">Antonio Torralba</a>, 1146 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a><br> 1147 In CVPR (oral, best paper finalist), 2022. <br> 1148 [<a href="https://arxiv.org/abs/2112.05143">Paper</a>] 1149 [<a href="https://www.wpeebles.com/gangealing.html">Webpage</a>] 1150 [<a href="https://github.com/wpeebles/gangealing">GitHub</a>] 1151 [<a href="https://www.youtube.com/watch?v=Qa1ASS_NuzE">Video</a>] 1152 [<a href="https://www.wpeebles.com/gangealing_bibtex.txt">Bibtex</a>] 1153 <br> 1154 </td> 1155 </tr> 1156 <tr> 1157 <td width="30%" align=center> 1158 <img width="180" align="center" src="index_files/arxiv2021_visionaid_teaser.jpg" border="0"> 1159 </td> 1160 <td>
1161 <span style="font-size: 12pt;"> 1162 <b>Ensembling Off-the-shelf Models for GAN Training</b> <br> 1163 <span style="font-size: 10pt;"> 1164 <a href="https://nupurkmr9.github.io/">Nupur Kumari</a>, 1165 Richard Zhang, 1166 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, 1167 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 1168 In CVPR (oral), 2022. <br> 1169 [<a href="https://arxiv.org/abs/2112.09130">Paper</a>] 1170 [<a href="https://www.cs.cmu.edu/~vision-aided-gan/">Webpage</a>] 1171 [<a href="https://github.com/nupurkmr9/vision-aided-gan">GitHub</a>] 1172 [<a href="https://www.youtube.com/watch?v=oHdyJNdQ9E4">Video</a>] 1173 [<a href="index_files/bibtex_arxiv2021_visionaid.txt">Bibtex</a>] 1174 <br> 1175 </td> 1176 </tr> 1177 <tr> 1178 <td width="30%" align=center> 1179 <!-- height="74" --> 1180 <!-- <center> --> 1181 <img width="240" align="center" src="https://www.cs.cmu.edu/~SAMInversion/resources/teaser_prepped.gif" border="0"> 1182 <!-- </center> --> 1183 </td> 1184 <td> 1185 <span style="font-size: 12pt;"> 1186 <b>Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing</b> <br> 1187 <span style="font-size: 10pt;"> 1188 <a href="https://gauravparmar.com/">Gaurav Parmar</a>, 1189 <a href="https://yijunmaverick.github.io/">Yijun Li</a>, 1190 <a href="https://research.adobe.com/person/jingwan-lu/">Jingwan Lu</a>, 1191 Richard Zhang, 1192 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 1193 <a href="http://krsingh.cs.ucdavis.edu/">Krishna Kumar Singh</a> 1194 <br> 1195 In CVPR, 2022. <br> 1196 [<a href="https://arxiv.org/abs/2206.08357">Paper</a>] 1197 [<a href="https://www.cs.cmu.edu/~SAMInversion/">Webpage</a>] 1198 [<a href="https://github.com/adobe-research/sam_inversion">GitHub</a>] 1199 [<a href="https://www.cs.cmu.edu/~SAMInversion/resources/bibtex.txt">Bibtex</a>] 1200 <br> 1201 </td> 1202 </tr> 1203 <tr> 1204 <td width="30%" align=center> 1205 <!-- height="74" --> 1206 <!-- <center> --> 1207 <img width="260" align="center" src="https://raw.githubusercontent.com/GaParmar/clean-fid/main/docs/images/resize_circle.png" border="0"> 1208 <!-- </center> --> 1209 </td> 1210 <td> 1211 <span style="font-size: 12pt;"> 1212 <b>On Aliased Resizing Libraries and Surprising Subtleties in FID Calculation</b> <br> 1213 <span style="font-size: 10pt;"> 1214 <a href="https://gauravparmar.com/">Gaurav Parmar</a>, Richard Zhang, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 1215 In CVPR, 2022. <br> 1216 [<a href="https://arxiv.org/abs/2104.11222">Paper</a>] 1217 [<a href="https://www.cs.cmu.edu/~clean-fid/">Webpage</a>] 1218 [<a href="https://github.com/GaParmar/clean-fid">GitHub</a>] 1219 [<a href="https://github.com/GaParmar/clean-fid#citation">Bibtex</a>] 1220 <br> 1221 </td> 1222 </tr> 1223 <tr> 1224 <td width="30%" align=center> 1225 <!-- height="74" --> 1226 <!-- <center> --> 1227 <img width="260" align="center" src="index_files/editnerf.png" border="0"> 1228 <!-- </center> --> 1229 </td> 1230 <td>
1231 <span style="font-size: 12pt;"> 1232 <b>Editing Conditional Radiance Fields</b> <br> 1233 <span style="font-size: 10pt;"> 1234 <a href="http://people.csail.mit.edu/stevenliu/">Steven Liu</a>, <a href="https://people.csail.mit.edu/xiuming/">Xiuming Zhang</a>, <a href="https://ztzhang.info/">Zhoutong Zhang</a>, Richard Zhang, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="http://bryanrussell.org/">Bryan Russell</a><br> 1235 In ICCV, 2021. <br> 1236 [<a href="https://arxiv.org/abs/2105.06466">Paper</a>] 1237 [<a href="http://editnerf.csail.mit.edu/">Webpage</a>] 1238 [<a href="https://github.com/stevliu/editnerf">GitHub</a>] 1239 [<a href="https://www.youtube.com/watch?v=9qwRD4ejOpw">Video</a>] 1240 [<a href="https://colab.research.google.com/github/stevliu/editnerf/blob/master/editnerf.ipynb">Demo</a>] 1241 [<a href="https://github.com/stevliu/editnerf#citation">Bibtex</a>] 1242 <br> 1243 </td> 1244 </tr> 1245 <tr> 1246 <td width="30%" align=center> 1247 <!-- height="74" --> 1248 <!-- <center> --> 1249 <img width="200" align="center" src="index_files/cfl_teaser.png" border="0"> 1250 <!-- </center> --> 1251 </td> 1252 <td> 1253 <span style="font-size: 12pt;"> 1254 <b>Contrastive Feature Loss for Image Prediction</b> <br> 1255 <span style="font-size: 10pt;"> 1256 <a href="https://www.alexandonian.com/">Alex Andonian</a>, 1257 <a href="https://taesung.me/">Taesung Park</a>, 1258 <a href="http://bryanrussell.org/">Bryan Russell</a>, 1259 <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, 1260 <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, 1261 Richard Zhang.<br> 1262 In ICCV AIM Workshop, 2021. <br> 1263 [<a href="https://arxiv.org/abs/2111.06934">Paper</a>] 1264 [<a href="https://github.com/alexandonian/contrastive-feature-loss">GitHub</a>] 1265 [<a href="index_files/bibtex_iccvaim21_cfl.txt">Bibtex</a>] 1266 <br> 1267 </td> 1268 </tr> 1269 <tr> 1270 <td width="30%" align=center> 1271 <!-- height="74" --> 1272 <!-- <center> --> 1273 <img width="180" align="center" src="https://github.com/chail/gan-ensembling/blob/main/img/teaser.gif?raw=true" border="0"> 1274 <!-- </center> --> 1275 </td> 1276 <td> 1277 <span style="font-size: 12pt;"> 1278 <b>Ensembling with Deep Generative Views</b> <br> 1279 <span style="font-size: 10pt;"> 1280 <a href="http://people.csail.mit.edu/lrchai/">Lucy Chai</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, Richard Zhang<br> 1281 In CVPR, 2021. <br> 1282 [<a href="https://arxiv.org/abs/2104.14551">Paper</a>] 1283 [<a href="https://chail.github.io/gan-ensembling/">Webpage</a>] 1284 [<a href="https://github.com/chail/gan-ensembling">GitHub</a>] 1285 [<a href="https://www.youtube.com/channel/UCty2ywzQwRx-qpbV1S8EiKQ">Video</a>] 1286 [<a href="https://colab.research.google.com/drive/1-qZBjn07KlWv27kKQGaKOXMBgP-Fb
12860Ws?usp=sharing">Colab</a>] 1287 [<a href="https://chail.github.io/gan-ensembling/bibtex.txt">Bibtex</a>] 1288 <br> 1289 </td> 1290 </tr> 1291 <tr> 1292 <td width="30%" align=center> 1293 <!-- height="74" --> 1294 <!-- <center> --> 1295 <img width="260" align="center" src="https://github.com/utkarshojha/few-shot-gan-adaptation/blob/gh-pages/resources/concept.gif?raw=true" border="0"> 1296 <!-- </center> --> 1297 </td> 1298 <td> 1299 <span style="font-size: 12pt;"> 1300 <b>Few-shot Image Generation via Cross-domain Correspondence</b> <br> 1301 <span style="font-size: 10pt;"> 1302 <a href="https://utkarshojha.github.io/">Utkarsh Ojha</a>, <a href="https://yijunmaverick.github.io/">Yijun Li</a>, <a href="https://research.adobe.com/person/jingwan-lu/">Jingwan Lu</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, <a href="https://web.cs.ucdavis.edu/~yjlee/">Yong Jae Lee</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, Richard Zhang<br> 1303 In CVPR, 2021. <br> 1304 [<a href="https://arxiv.org/abs/2104.06820">Paper</a>] 1305 [<a href="https://utkarshojha.github.io/few-shot-gan-adaptation/">Webpage</a>] 1306 [<a href="https://github.com/utkarshojha/few-shot-gan-adaptation">GitHub</a>] 1307 [<a href="https://www.youtube.com/watch?v=GCDm8hOlpHs">Video</a>] 1308 [<a href="https://utkarshojha.github.io/few-shot-gan-adaptation/resources/bibtex.txt">Bibtex</a>] 1309 <br> 1310 </td> 1311 </tr> 1312 <tr> 1313 <td width="30%" align=center> 1314 <!-- height="74" --> 1315 <!-- <center> --> 1316 <img width="260" align="center" src="https://hanlab18.mit.edu/projects/anycost-gan/images/flexible.gif" border="0"> 1317 <!-- </center> --> 1318 </td> 1319 <td> 1320 <span style="font-size: 12pt;"> 1321 <b>Anycost GANs for Interactive Image Synthesis and Editing</b> <br> 1322 <span style="font-size: 10pt;"> 1323 <a href="http://linji.me/">Ji Lin</a>, Richard Zhang, Frieder Ganz, <a href="https://songhan.mit.edu/">Song Han</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 1324 In CVPR, 2021. <br> 1325 [<a href="https://arxiv.org/abs/2103.03243">Paper</a>] 1326 [<a href="https://hanlab18.mit.edu/projects/anycost-gan/">Webpage</a>] 1327 [<a href="https://www.youtube.com/watch?v=_yEziPl9AkM">Video</a>] 1328 [<a href="https://github.com/mit-han-lab/anycost-gan">GitHub</a>] 1329 [<a href="https://github.com/mit-han-lab/anycost-gan#citation">Bibtex</a>] 1330 <br> 1331 </td> 1332 </tr> 1333 <tr> 1334 <td width="30%" align=center> 1335 <!-- height="74" --> 1336 <!-- <center> --> 1337 <img height="90" align="center" src="index_files/asapnet_teaser.png" border="0"> 1338 <!-- </center> --> 1339 </td> 1340 <td> 1341 <span style="font-size: 12pt;"> 1342 <b>Spatially-Adaptive Pixelwise Networks for Fast Image Translation</b> <br> 1343 <span style="font-size: 10pt;"> 1344 <a href="https://stamarot.webgr.technion.ac.il/">Tamar Rott Shaham</a>, <a href="http://www.mgharbi.com/">Michaël Gharbi</a>, Richard Zhang, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="https://tomer.net.technion.ac.il/">Tomer Michaeli</a><br> 1345 In CVPR, 2021. <br> 1346 [<a href="https://arxiv.org/abs/2012.02992">Paper</a>] 1347 [<a href="https://tamarott.github.io/ASAPNet_web/">Webpage</a>] 1348 [<a href="https://tamarott.github.io/ASAPNet_web/resources/bibtex.txt">Bibtex</a>] 1349 <br> 1350 </td> 1351 </tr> 1352 <tr> 1353 <td width="30%" align=center> 1354 <!-- height="74" --> 1355 <!-- <center> --> 1356 <img width="220" align="center" src="./index_files/cdpam_teaser.jpg" border="0"> 1357 <!-- </center> --> 1358 </td> 1359 <td>
1360 <span style="font-size: 12pt;"> 1361 <b>CDPAM: Contrastive Learning for Perceptual Audio Similarity</b> <br> 1362 <span style="font-size: 10pt;"> 1363 <a href="https://www.cs.princeton.edu/~pmanocha/">Pranay Manocha</a>, <a href="https://research.adobe.com/person/zeyu-jin/">Zeyu Jin</a>, Richard Zhang, <a href="https://www.cs.princeton.edu/~af/">Adam Finkelstein</a><br> 1364 In ICASSP, 2021. <br> 1365 [<a href="https://arxiv.org/abs/2102.05109">Paper</a>] 1366 [<a href="https://pixl.cs.princeton.edu/pubs/Manocha_2021_CCL/index.php">Webpage</a>] 1367 [<a href="https://github.com/pranaymanocha/PerceptualAudio">GitHub</a>] 1368 [<a href="./index_files/bibtex_icassp2021_audio.txt">Bibtex</a>] 1369 <br> 1370 </td> 1371 </tr> 1372 <tr> 1373 <td width="30%" align=center> 1374 <!-- height="74" --> 1375 <!-- <center> --> 1376 <img height="80" align="center" src="https://taesung.me/SwappingAutoencoder/index_files/church_style_swaps.gif" border="0"> 1377 <img height="80" align="center" src="https://taesung.me/SwappingAutoencoder/index_files/tree_smaller.gif" border="0"> 1378 <!-- </center> --> 1379 </td> 1380 <td> 1381 <span style="font-size: 12pt;"> 1382 <b>Swapping Autoencoder for Deep Image Manipulation</b> <br> 1383 <span style="font-size: 10pt;"> 1384 <a href="https://taesung.me/">Taesung Park</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="http://www.oliverwang.info/">Oliver Wang</a>, <a href="https://research.adobe.com/person/jingwan-lu/">Jingwan Lu</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, Richard Zhang<br> 1385 In NeurIPS, 2020. <br> 1386 [<a href="https://arxiv.org/abs/2007.00653">Paper</a>] 1387 [<a href="https://taesung.me/SwappingAutoencoder">Webpage</a>] 1388 [<a href="https://github.com/taesungp/swapping-autoencoder-pytorch">GitHub</a>] 1389 [<a href="https://www.youtube.com/watch?v=0elW11wRNpg&feature=emb_title">Video</a>] 1390 [<a href="https://taesung.me/SwappingAutoencoder/index_files/bibtex_arxiv2020.txt">Bibtex</a>] 1391 <br> 1392 </td> 1393 </tr> 1394 <tr> 1395 <td width="30%" align=center> 1396 <!-- height="74" --> 1397 <!-- <center> --> 1398 <img height="100" align="center" src="./index_files/fewshot_neurips20.jpg" border="0"> 1399 <!-- </center> --> 1400 </td> 1401 <td> 1402 <span style="font-size: 12pt;"> 1403 <b>Few-shot Image Generation with Elastic Weight Consolidation</b> <br> 1404 <span style="font-size: 10pt;"> 1405 <a href="https://yijunmaverick.github.io/">Yijun Li</a>, Richard Zhang, <a href="https://research.adobe.com/person/jingwan-lu/">Jingwan Lu</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a><br> 1406 In NeurIPS, 2020. <br> 1407 [<a href="https://arxiv.org/abs/2012.02780">Paper</a>] 1408 [<a href="https://proceedings.neurips.cc/paper/2020/file/b6d767d2f8ed5d21a44b0e5886680cb9-Supplemental.pdf">Supplemental</a>] 1409 [<a href="https://yijunmaverick.github.io/publications/ewc/">Webpage</a>] 1410 [<a href="./index_files/bibtex_fewshot_neurips20.txt">Bibtex</a>] 1411 <br> 1412 </td> 1413 </tr> 1414 <tr> 1415 <td width="30%" align=center> 1416 <!-- height="74" --> 1417 <!-- <center> --> 1418 <img height="100" align="center" src="index_files/eccv2020_cut.jpg" border="0"> 1419 <!-- <img height="110" align="center" src="index_files/eccv2020_cut.jpg" border="0"> --> 1420 <!-- </center> --> 1421 </td> 1422 <td>
1423 <span style="font-size: 12pt;"> 1424 <b>Contrastive Learning for Unpaired Image-to-Image Translation</b> <br> 1425 <span style="font-size: 10pt;"> 1426 <a href="https://taesung.me/">Taesung Park</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, Richard Zhang, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a><br> 1427 In ECCV, 2020. <br> 1428 [<a href="https://arxiv.org/abs/2007.15651">Paper</a>] 1429 [<a href="http://taesung.me/ContrastiveUnpairedTranslation">Webpage</a>] 1430 [<a href="https://github.com/taesungp/contrastive-unpaired-translation">GitHub</a>] 1431 [<a href="https://www.youtube.com/watch?v=Llg0vE_MVgk&feature=emb_title">Teaser</a>] 1432 [<a href="https://www.youtube.com/watch?v=jSGOzjmN8q0">Video</a>] 1433 [<a href="http://taesung.me/ContrastiveUnpairedTranslation/index_files/bibtex_eccv2020.txt">Bibtex</a>] 1434 <br> 1435 </td> 1436 </tr> 1437 1438 <tr> 1439 <td width="30%" align=left> 1440 <img width="260" align="center" src="./index_files/arxiv2020_project_teaser.jpg" border="0"> 1441 </td> 1442 <td> 1443 <span style="font-size: 12pt;"> 1444 <b> Transforming and Projecting Images into Class-conditional Generative Networks</b><br> 1445 <span style="font-size: 10pt;"> 1446 <a href="http://people.csail.mit.edu/minhuh/">Minyoung Huh</a>, Richard Zhang, <a href="http://people.eecs.berkeley.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="http://people.csail.mit.edu/sparis/">Sylvain Paris</a>, <a href="https://www.dgp.toronto.edu/~hertzman/">Aaron Hertzmann</a><br> 1447 In ECCV (oral), 2020. <br> 1448 <!-- [<a href="">Paper</a>] --> 1449 [<a href="https://arxiv.org/abs/2005.01703">Paper</a>] 1450 [<a href="https://minyoungg.github.io/pix2latent/">Webpage</a>] 1451 [<a href="https://github.com/minyoungg/pix2latent">GitHub</a>] 1452 [<a href="./index_files/bibtex_arxiv2020_trans_proj.txt">Bibtex</a>] 1453 <br> 1454 </td> 1455 </tr> 1456 <tr> 1457 <td width="30%" align=left> 1458 <!-- height="74" --> 1459 <!-- <center> --> 1460 <img width="260" align="center" src="./index_files/audio_teaser.jpg" border="0"> 1461 <!-- </center> --> 1462 </td> 1463 <td> 1464 <span style="font-size: 12pt;"> 1465 <b>A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences</b> <br> 1466 <span style="font-size: 10pt;"> 1467 <a href="https://www.cs.princeton.edu/~pmanocha/">Pranay Manocha</a>, <a href="https://www.cs.princeton.edu/~af/">Adam Finkelstein</a>, Richard Zhang, <a href="https://ccrma.stanford.edu/~njb/">Nicholas J. Bryan</a>, <a href="https://ccrma.stanford.edu/~gautham/Site/Gautham_J._Mysore.html">Gautham J. Mysore</a>, <a href="https://research.adobe.com/person/zeyu-jin/">Zeyu Jin</a><br> 1468 In Interspeech, 2020. <br> 1469 [<a href="https://arxiv.org/abs/2001.04460">Paper</a>] 1470 [<a href="https://gfx.cs.princeton.edu/pubs/Manocha_2020_ADP/">Webpage</a>] 1471 [<a href="https://github.com/pranaymanocha/PerceptualAudio">GitHub</a>] 1472 [<a href="./index_files/bibtex_arxiv2020_audio.txt">Bibtex</a>] 1473 <br> 1474 </td> 1475 </tr> 1476 <tr> 1477 <td width="30%" align=center> 1478 <!-- height="74" --> 1479 <!-- <center> --> 1480 <img width="220" align="center" src="./index_files/cnndetect_teaser2.png" border="0"> 1481 <!-- </center> --> 1482 </td> 1483 <td>
1484 <span style="font-size: 12pt;"> 1485 <b>CNN-generated images are surprisingly easy to spot...for now</b> <br> 1486 <span style="font-size: 10pt;"> 1487 <a href="https://peterwang512.github.io">Sheng-Yu Wang</a>, <a href="http://www.oliverwang.info/">Oliver Wang</a>, Richard Zhang, <a href="http://andrewowens.com">Andrew Owens</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a> <br> 1488 In CVPR, 2020 (oral). <br> 1489 [<a href="https://arxiv.org/abs/1912.11035">Paper</a>] 1490 [<a href="https://peterwang512.github.io/CNNDetection/">Webpage</a>] 1491 [<a href="https://github.com/PeterWang512/CNNDetection">GitHub</a>] 1492 [<a href="https://www.youtube.com/watch?v=98bCHTkp5sE">Talk</a>] 1493 [<a href="https://peterwang512.github.io/CNNDetection/bibtex.txt">Bibtex</a>] 1494 <br> 1495 </td> 1496 </tr> 1497 1498 <tr> 1499 <td width="30%" align=left> 1500 <!-- height="74" --> 1501 <img width="250" align="center" src="./index_files/shape_2019_teaser.jpg" border="0"> 1502 </td> 1503 <td> 1504 <span style="font-size: 12pt;"> 1505 <b>Deep Parametric Shape Predictions using Distance Fields</b> <br> 1506 <span style="font-size: 10pt;"> 1507 <a href="http://people.csail.mit.edu/smirnov/">Dmitriy Smirnov</a>, 1508 <a href="https://research.adobe.com/person/matt-fisher/">Matthew Fisher</a>, 1509 <a href="https://research.adobe.com/person/vladimir-kim/">Vladimir G. Kim</a>, 1510 Richard Zhang, 1511 <a href="https://people.csail.mit.edu/jsolomon/">Justin Solomon</a><br> 1512 In CVPR, 2020. <br> 1513 [<a href="https://arxiv.org/abs/1904.08921">Paper</a>] 1514 [<a href="https://people.csail.mit.edu/smirnov/deep-parametric-shapes/">Webpage</a>] 1515 [<a href="https://github.com/dmsm/DeepParametricShapes">GitHub</a>] 1516 [<a href="https://www.youtube.com/watch?v=v_0UrjbTtHg">Video</a>] 1517 [<a href="./index_files/bibtex_arxiv2019_shape.txt">Bibtex</a>] 1518 <br> 1519 </td> 1520 </tr> 1521 1522 1523 <tr> 1524 <td width="30%" align=left> 1525 <!-- height="74" --> 1526 <!-- <center> --> 1527 <div style="width: 260; height: 80; margin: -10px 0px 0px 0px; overflow: hidden"> 1528 <img width="75" align="center" src="./index_files/morph_1028_AB.jpg_100619_AB.jpg.gif" border="0"> 1529 <img width="75" align="center" src="./index_files/morph_7994928.362576.jpg_7590611.3.jpg.gif" border="0"> 1530 <img width="100" align="center" src="./index_files/morph_3113.png_3938.png.gif" border="0"> 1531 </div> 1532 <!-- <img width="80" align="center" src="./index_files/morph_100938_AB.jpg_27721_AB.jpg.gif" border="0"> --> 1533 <!-- <img width="80" align="center" src="./index_files/morph_f58a26c915e7a1dceae7a0fa074b4a2a_1.png_7805239ad1e40e07c69d7040c52664c5_1.png.gif" border="0"> --> 1534 <!-- </center> --> 1535 </td> 1536 <td> 1537 <span style="font-size: 12pt;"> 1538 <b> Image Morphing with Perceptual Constraints and STN Alignment </b> <br> 1539 <span style="font-size: 10pt;"> 1540 <a href="https://www.cs.tau.ac.il/~noafish/">Noa Fish</a>, Richard Zhang, Lilach Perry, <a href="https://www.cs.tau.ac.il/~dcor/index.html">Daniel Cohen-Or</a>, <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="http://www.connellybarnes.com/">Connelly Barnes</a><br> 1541 In CGF, 2020. <br> 1542 [<a href="https://arxiv.org/abs/2004.14071">Paper</a>] 1543 [<a href="https://github.com/noafish/MorphGAN">GitHub</a>] 1544 [<a href="./index_files/bibtex_arxiv2020_morph.txt">Bibtex</a>] 1545 <br> 1546 </td> 1547 </tr> 1548 1549 1550<!-- <tr>
1550<td width="30%" align=left> 1551 <span style="font-size: 16pt;"><b>2019</b></span> 1552 </td></tr> --> 1553 1554 <tr> 1555 <td width="30%" align=left> 1556 <!-- height="74" --> 1557 <!-- <center> --> 1558 <img width="125" align="center" src="./index_files/aacnns_2019_teaser.gif" border="0"> 1559 <img width="125" align="center" src="./index_files/aacnns_2019_teaser2.gif" border="0"> 1560 <!-- </center> --> 1561 </td> 1562 <td> 1563 <span style="font-size: 12pt;"> 1564 <b>Making Convolutional Networks Shift-Invariant Again</b> <br> 1565 <span style="font-size: 10pt;"> 1566 Richard Zhang <br> 1567 In ICML, 2019. <br> 1568 <!-- [<a href="https://richzhang.github.io/antialiased-cnns/resources/camera-ready.pdf">Paper</a>] --> 1569 [<a href="https://arxiv.org/abs/1904.11486">Paper</a>] 1570 [<a href="https://richzhang.github.io/antialiased-cnns/">Webpage</a>] 1571 [<a href="https://github.com/adobe/antialiased-cnns">GitHub</a>] 1572 [<a href='https://www.youtube.com/watch?v=HjewNBZz00w&feature=youtu.be'>Talk</a>] 1573 [<a href='https://www.dropbox.com/s/4mco6s76d9hi00n/antialiasing_cnns.pptx?dl=0'>Slides</a> (129mb)] 1574 [<a href="https://www.dropbox.com/s/dhf2gqt14sq76q7/poster_icml.pdf?dl=0">Poster</a>] 1575 [<a href="./index_files/bibtex_icml2019.txt">Bibtex</a>] 1576 <br> 1577 </td> 1578 </tr> 1579 <tr> 1580 <td width="30%" align=left> 1581 <!-- height="74" --> 1582 <!-- <center> --> 1583 <img width="250" align="center" src="./index_files/falteaser.png" border="0"> 1584 <!-- </center> --> 1585 </td> 1586 <td> 1587 <span style="font-size: 12pt;"> 1588 <b>Detecting Photoshopped Faces by Scripting Photoshop</b> <br> 1589 <span style="font-size: 10pt;"> 1590 <a href="https://peterwang512.github.io/">Sheng-Yu Wang</a>, <a href="http://www.oliverwang.info/">Oliver Wang</a>, <a href="http://andrewowens.com">Andrew Owens</a>, Richard Zhang, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a> <br> 1591 In ICCV, 2019. <br> 1592 [<a href="https://arxiv.org/abs/1906.05856">Paper</a>] 1593 [<a href="https://peterwang512.github.io/FALdetector/">Webpage</a>] 1594 [<a href="https://github.com/peterwang512/FALdetector">GitHub</a>] 1595 [<a href="https://www.youtube.com/watch?v=TUootD36Xm0">Video</a>] 1596 [<a href="https://www.dropbox.com/s/qn4c19134zjziyi/%5BFinal%5D%20ICCV%20Poster.pdf?dl=0">Poster</a>] 1597 [<a href="https://www.youtube.com/watch?v=21lj8tCSMkg">Adobe Max</a>] 1598 [<a href="https://business.adobe.com/blog/the-latest/adobe-research-and-uc-berkeley-detecting-facial-manipulations-in-adobe-photoshop">Adobe Blog</a>] 1599 [<a href="./index_files/bibtex_fal2019.txt">Bibtex</a>] 1600 <br> 1601 </td> 1602 </tr> 1603 1604 <tr> 1605 <td width="30%" align=left> 1606 <!-- height="74" --> 1607 <img width="125" align="center" src="./index_files/isketchnfill_teaser.gif" border="0"> 1608 <img width="125" align="center" src="./index_files/isketchnfill_teaser2.gif" border="0"> 1609 </td> 1610 <td> 1611 <span style="font-size: 12pt;"> 1612 <b>Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation</b> <br>
1613 <span style="font-size: 10pt;"> 1614 <a href="https://arnabgho.github.io/">Arnab Ghosh</a>, 1615 Richard Zhang, 1616 <a href="https://puneetkdokania.github.io/">Puneet Dokania</a>, 1617 <a href="http://www.oliverwang.info/">Oliver Wang</a>, 1618 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, 1619 <a href="http://www.robots.ox.ac.uk/~phst/">Philip H.S. Torr</a>, 1620 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a><br> 1621 In ICCV, 2019. <br> 1622 [<a href="https://arxiv.org/abs/1909.11081">Paper</a>] 1623 [<a href="https://arnabgho.github.io/iSketchNFill/">Webpage</a>] 1624 [<a href="https://github.com/arnabgho/iSketchNFill">GitHub</a>] 1625 [<a href="https://www.youtube.com/watch?v=T9xtpAMUDps">Video</a>] 1626 [<a href="./index_files/bibtex_iccv2019_isketchnfill.txt">Bibtex</a>] 1627 <br> 1628 </td> 1629 </tr> 1630 1631 1632<!-- <tr><td width="30%" align=left> 1633 <span style="font-size: 16pt;"><b>2018</b></span> 1634 </td></tr> --> 1635 <tr> 1636 <td width="30%" align=left> 1637 <!-- height="74" --> 1638 <img width="250" align="center" src="./index_files/perceptual_teaser.jpg" border="0"> 1639 </td> 1640 <td> 1641 <span style="font-size: 12pt;"> 1642 <b>The Unreasonable Effectiveness of Deep Features as a Perceptual Metric</b> <br> 1643 <span style="font-size: 10pt;"> 1644 Richard Zhang, <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, 1645 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a>, <a href="http://www.oliverwang.info/">Oliver Wang</a><br> 1646 In CVPR, 2018. <br> 1647 [<a href="http://arxiv.org/abs/1801.03924">Paper</a>] 1648 [<a href="https://richzhang.github.io/PerceptualSimilarity/">Webpage</a>] 1649 [<a href="https://github.com/richzhang/PerceptualSimilarity">GitHub</a>] 1650 [<a href="https://richzhang.github.io/PerceptualSimilarity/index_files/poster_cvpr.pdf">Poster</a>] 1651 [<a href="https://research.adobe.com/with-deep-learning-computers-see-images-more-like-humans-do/">Adobe Blog</a>] 1652 [<a href="https://www.youtube.com/watch?v=DglrYx9F3UU">Two Min Papers</a>] 1653 [<a href="./index_files/bibtex_cvpr2018.txt">Bibtex</a>] 1654 <br> 1655 </td> 1656 </tr> 1657 <tr> 1658 <td width="30%" align=left> 1659 <!-- height="74" --> 1660 <img width="250" align="center" src="./index_files/savp3.gif" border="0"> 1661 </td> 1662 <td> 1663 <span style="font-size: 12pt;"> 1664 <b>Stochastic Adversarial Video Prediction</b> <br> 1665 <span style="font-size: 10pt;"> 1666 <a href="http://people.eecs.berkeley.edu/~alexlee_gk/index.html">Alex X. Lee</a>, Richard Zhang, 1667 <a href="https://febert.github.io/">Frederik Ebert</a>, <a href="http://people.eecs.berkeley.edu/~pabbeel/">Pieter Abbeel</a>, <a href="https://people.eecs.berkeley.edu/~cbfinn/">Chelsea Finn</a>, <a href="https://people.eecs.berkeley.edu/~svlevine/">Sergey Levine</a> <br> 1668 In ArXiv, 2018. <br> 1669 [<a href="https://arxiv.org/abs/1804.01523">Paper</a>] 1670 [<a href="https://alexlee-gk.github.io/video_prediction/">Webpage</a>] 1671 [<a href="https://github.com/alexlee-gk/video_prediction">GitHub</a>] 1672 [<a href="./index_files/bibtex_savp.txt">Bibtex</a>] 1673 <br> 1674 </td> 1675 </tr> 1676 1677 1678<!-- <tr>
1678<td width="30%" align=left> 1679 <span style="font-size: 16pt;"><b>2017</b></span> 1680 </td></tr> --> 1681 1682 <tr> 1683 <td width="30%" align=left> 1684 <!-- height="74" --> 1685 <img width="250" align="center" src="./index_files/nips2017.jpg" border="0"> 1686 </td> 1687 <td> 1688 <span style="font-size: 12pt;"> 1689 <b>Toward Multimodal Image-to-Image Translation</b> <br> 1690 <span style="font-size: 10pt;"> 1691 <a href="http://people.eecs.berkeley.edu/~junyanz/">Jun-Yan Zhu</a>, Richard Zhang, <a href="http://people.eecs.berkeley.edu/~pathak/">Deepak Pathak</a>, <a href="https://people.eecs.berkeley.edu/~trevor/">Trevor Darrell</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, <a href="http://www.oliverwang.info/">Oliver Wang</a>, 1692 <a href="https://research.adobe.com/person/eli-shechtman/">Eli Shechtman</a> <br> 1693 In NIPS, 2017. <br> 1694 [<a href="https://arxiv.org/abs/1711.11586">Paper</a>] 1695 <!-- <a href="https://papers.nips.cc/paper/6650-toward-multimodal-image-to-image-translation">Official</a>] --> 1696 [<a href="https://junyanz.github.io/BicycleGAN/">Webpage</a>] 1697 [<a href="https://github.com/junyanz/BicycleGAN">GitHub</a>] 1698 [Video (<a href="https://www.youtube.com/watch?v=JvGysD2EFhw">YouTube</a>)(<a href="http://efrosgans.eecs.berkeley.edu/BicycleGAN/video_extended.mp4">mp4</a>)] 1699 [<a href="http://junyanz.github.io/BicycleGAN/index_files/poster_nips_v3.pdf">Poster</a>] 1700 [<a href="https://www.youtube.com/watch?v=XcxzKLrCpyk">Two Min Papers</a>] 1701 [<a href="./index_files/bibtex_nips2017.txt">Bibtex</a>] 1702 <br> 1703 </td> 1704 </tr> 1705 <tr> 1706 <td width="30%" align=left> 1707 <!-- height="74" --> 1708 <a href="http://richzhang.github.io/ideepcolor"><img width="250" align="center" src="./index_files/siggraph2017_update.jpg" border="0"></a> 1709 </td> 1710 <td> 1711 <span style="font-size: 12pt;"> 1712 <b>Real-Time User-Guided Image Colorization with Learned Deep Priors</b> <br> 1713 <span style="font-size: 10pt;"> 1714 Richard Zhang*, <a href="http://people.eecs.berkeley.edu/~junyanz/">Jun-Yan Zhu</a>*, <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, <a href="http://young-geng.xyz/">Xinyang Geng</a>, <a href="http://www.cs.utexas.edu/~alin/">Angela S. Lin</a>, <a href="https://tianheyu927.github.io/">Tianhe Yu</a>, 1715 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a> <br> 1716 (*equal contribution) <br> 1717 In SIGGRAPH, 2017. <br> 1718 [<a href="https://arxiv.org/abs/1705.02999">Paper</a>] 1719 <!-- <a href="https://dl.acm.org/citation.cfm?id=3073703">Official</a>] --> 1720 [<a href="https://richzhang.github.io/InteractiveColorization/">Webpage</a>] 1721 [<a href="https://youtu.be/eiFzQI7LzO0?t=5690">Fastforward</a>] 1722 [<a href="https://www.youtube.com/watch?v=rp5LUSbdsys">Talk</a>] 1723 [Video (<a href="https://www.youtube.com/watch?v=eL5ilZgM89Q&feature=youtu.be">YouTube</a>)(<a href="https://www.dropbox.com/s/mfi66auuv7qzyx0/iColor_release.mp4?dl=0">mp4</a>)] 1724 [<a href="http://video.tv.adobe.com/v/28291">PSE 2020</a>] 1725 [<a href="https://github.com/junyanz/interactive-deep-colorization">GitHub</a>] 1726 [<a href="https://www.dropbox.com/s/urmifx558nw0ogi/release.pptx?dl=0">Slides</a> (141mb)] 1727 [<a href="./index_files/bibtex_siggraph2017.txt">Bibtex</a>] 1728 <br> 1729 </td> 1730 </tr> 1731 <tr> 1732 <td width="30%" align=left> 1733 <a href="http://richzhang.github.io/splitbrainauto"><img width="250" align="center" src="./index_files/cvpr2017_splitbrain.png" border="0"></a> 1734 </td> 1735 <td>
1736 <span style="font-size: 12pt;"> 1737 <b>Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction</b><br> 1738 <span style="font-size: 10pt;"> 1739 Richard Zhang, <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, 1740 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a> <br> 1741 In CVPR, 2017. 1742 <br> 1743 [<a href="https://arxiv.org/abs/1611.09842">Paper</a>] 1744 <!-- (<a href="http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Split-Brain_Autoencoders_Unsupervised_CVPR_2017_paper.html">official</a>)] --> 1745 [<a href="http://richzhang.github.io/splitbrainauto">Webpage</a>] 1746 [<a href="https://github.com/richzhang/splitbrainauto">GitHub</a>] 1747 [<a href="https://richzhang.github.io/splitbrainauto/index_files/poster_cvpr.pdf">Poster</a>] 1748 [<a href="https://www.youtube.com/watch?v=FTzcFsz2xqw">Seminar Talk</a>] 1749 [<a href="./index_files/bibtex_cvpr2017_splitbrain.txt">Bibtex</a>]</span> 1750 </td> 1751 </tr> 1752 1753 1754<!-- <tr><td width="30%" align=left> 1755 <span style="font-size: 16pt;"><b>2016</b></span> 1756 </td></tr> --> 1757 1758 <tr> 1759 <td width="30%" align=left> 1760 <!-- height="90" --> 1761 <a href="http://richzhang.github.io/colorization/"><img width="250" align="center" src="./index_files/arxiv2016_colorization.jpg" border="0"></a> 1762 </td> 1763 <td> 1764 <span style="font-size: 12pt;"><b>Colorful Image Colorization</span></b><br> 1765 <span style="font-size: 10pt;"> 1766 Richard Zhang, <a href="http://web.mit.edu/phillipi/">Phillip Isola</a>, 1767 <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a> <br> 1768 In ECCV, 2016 (oral). 1769 <br> 1770 [<a href="https://arxiv.org/abs/1603.08511">Paper</a>] 1771 <!-- <a href="https://link.springer.com/chapter/10.1007/978-3-319-46487-9_40">Official</a>] --> 1772 [<a href="http://richzhang.github.io/colorization/">Webpage</a>] 1773 [<a href="https://github.com/richzhang/colorization">GitHub</a>] 1774 [<a href="https://www.youtube.com/watch?v=4xoTD58Wt-0">Talk</a>] 1775 [<a href="https://www.dropbox.com/s/sa8m3y1ymj0ihct/presentation_eccv_release.pptx?dl=0">Slides</a> (138mb)] 1776 [<a href="http://www.eccv2016.org/files/posters/O-2B-03.pdf">Poster</a>] 1777 [<a href="./index_files/bibtex_eccv2016_colorization.txt">Bibtex</a>] 1778 </td> 1779 </tr> 1780 1781<!-- <tr><td width="30%" align=left> 1782 <span style="font-size: 16pt;"><b>2015</b></span> 1783 </td></tr> --> 1784 1785 <tr> 1786 <td width="30%" align=left> 1787 <img width="250" align="center" src="./index_files/icra2015.png" border="0"> 1788 </td> 1789 <td> 1790 <span style="font-size: 12pt;"> 1791 <b>Sensor Fusion for Semantic Segmentation of Urban Scenes</b><br> 1792 <span style="font-size: 10pt;"> 1793 Richard Zhang, <a href="https://www.linkedin.com/in/candrastefan/">Stefan Candra</a>, <a href="http://anp.lbl.gov/kai-vetter/">Kai Vetter</a>, 1794 <a href="http://www-video.eecs.berkeley.edu/~avz/">Avideh Zakhor</a> <br> 1795 In ICRA, 2015. 1796 <br> 1797 [Paper (<a href="./index_files/icra2015.pdf">pdf</a>)(<a href="http://ieeexplore.ieee.org/document/7139439/">official</a>)] 1798 1799 [<a href="./index_files/pres_icra2015.pdf">Slides</a>] 1800 [<a href="./index_files/poster_icra2015.pdf">Poster</a>] 1801 [<a href="https://www.youtube.com/watch?v=s9X63Ma3M0Y">Talk</a>] 1802 1803 [Annotations (<a href="http://www.eecs.berkeley.edu/~rich.zhang/projects/2015_ICRA_semanticsegmentation/KITTI_public.tar">tar</a>)(<a href="http://www.eecs.berkeley.edu/~rich.zhang/projects/2015_ICRA_semanticsegmentation/KITTI_public.zip">zip</a>) ]
1804 [<a href="./index_files/bibtex_icra2015.txt">Bibtex</a>] 1805 </span> 1806 </td> 1807 </tr> 1808 1809 1810<!-- <tr><td width="30%" align=left> 1811 <span style="font-size: 16pt;"><b>2014</b></span> 1812 </td></tr> --> 1813 1814 1815 <tr> 1816 <td width="30%" align="center"> 1817 <!-- height="100" --> 1818 <img height="95" horizontal-align="center" src="./index_files/wacv2014.png" border="0"> 1819 </td> 1820 <td> 1821 <span style="font-size: 12pt;"><b>Automatic Identification of Window Regions on Indoor Point Clouds Using LiDAR and Cameras</b><br> 1822 <span style="font-size: 10pt;"> 1823 Richard Zhang, 1824 <a href="http://www-video.eecs.berkeley.edu/~avz/">Avideh Zakhor</a> 1825 <br> 1826 In WACV, 2014. 1827 <br> 1828 [Paper (<a href="./index_files/wacv2014.pdf">pdf</a>)(<a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.649.303&rep=rep1&type=pdf">official</a>)] 1829 1830 [<a href="./index_files/bibtex_wacv2014.txt">Bibtex</a>] 1831 </span> 1832 </td> 1833 </tr> 1834 1835 </tbody></table> 1836 1837 <h2>Thesis </h2> 1838 <font face="helvetica, ariel, 'sans serif'"> 1839 <table cellspacing="15"> 1840 <tbody> 1841 <tr> 1842 <td width="30%" align=left> 1843 <img width="250" align="center" src="./index_files/berkeley_logo.png" border="0"> 1844 </td> 1845 <td> 1846 <span style="font-size: 12pt;"> 1847 <b>Image Synthesis for Self-Supervised Visual Representation Learning</b> <br> 1848 <span style="font-size: 10pt;"> 1849 Richard Zhang<br> 1850 <!-- Commitee: Alexei A. Efros, Trevor Darrell, Michael DeWeese.<br> --> 1851 Spring 2018.<br> 1852 [<a href="https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-36.html">Thesis</a>] 1853 [<a href="https://www.youtube.com/watch?v=aGhYitrOJRc">Dissertation Talk</a>] 1854 [<a href="https://youtu.be/IXG-uWFAkmM">Fast Forward</a>] 1855 [<a href="https://www.dropbox.com/s/96f0xhfwvjnbf52/presentation_dissertation.pptx?dl=0">Slides</a> (396 MB)] 1856 [<a href="./index_files/bibtex_thesis.txt">Bibtex</a>] 1857 <br> 1858 </td> 1859 </tr> 1860 </tbody></table> 1861 1862 1863 <h2>Organization, Committees </h2> 1864 <span style="font-size: 10pt;"> 1865 CVPR 2020, 2021, 2023, 2024, 2025, 2026 (Area Chair)<br> 1866 ECCV 2024 (Area Chair)<br> 1867 BMVC 2022 (Area Chair)<br> 1868 <a href="https://she-workshop.github.io/">Sketching for Human Expressivity (SHE)</a> at ECCV 2022 (co-organizer)<br> 1869 <a href="https://data.vision.ee.ethz.ch/cvl/aim19/">Advances in Image Manipulation (AIM)</a> at ICCV 2019 (co-organizer)<br> 1870 1871 <h2>Awards </h2> 1872 <span style="font-size: 10pt;"> 1873 Outstanding Area Chair, CVPR 2026<br> 1874 MIT Technology Review, <a href="https://www.technologyreview.com/innovator/richard-zhang/">35 Innovators Under 35</a>, 2023<br> 1875 Reviewer recognitions, CVPR 2019, NeurIPS 2019, ECCV 2020, NeurIPS 2020, ECCV 2022<br> 1876 Thesis Fast Forward, Best Presentation, SIGGRAPH 2018<br> 1877 <a href="https://research.adobe.com/fellowship/">Adobe Research Fellowship</a> 2017<br> 1878 1879 <h2>Media</h2> 1880 <!-- I was included on MIT Technology Review's list of <a href="https://www.technologyreview.com/innovator/richard-zhang/">Innovators Under 35</a>. --> 1881 Please see this Adobe <a href="https://blog.adobe.com/en/publish/2023/09/12/adobe-research-scientist-named-top-innovator-under-35-mit-technology-review">blog post</a>, <a href="https://www.youtube.com/watch?v=YQW32sf9noE">overview video</a> (5 min), or <a href="https://twimlai.com/podcast/twimlai/visual-generative-ai-ecosystem-challenges/">TWiML podcast</a> below (40 min) for more on our work on perception, generation, and forensics for GenAI.<br> 1882 <br> 1883 <iframe allow="autoplay *; encrypted-media *; fullscreen *; clipboard-write" frameborder="0" height="175" style="width:100%;max-width:660px;overflow:hidden;border-radius:10px;" sandbox="allow-forms allow-popups allow-same-origin allow-scripts allow-storage-access-by-user-activation allow-top-navigation-by-user-activation" src="https://embed.podcasts.apple.com/us/podcast/visual-generative-ai-ecosystem-challenges-with-richard/id1116303051?i=1000635452895"></iframe> 1884 1885 1886 1887<!-- <h2>Tech Transfers </h2>
1888 <span style="font-size: 10pt;"> 1889 Colorize Photo, Photoshop Elements 2020<br> 1890 Colorize, Photoshop Neural Filters 2020, 2021<br> 1891 Landscape Mixer, Photoshop Neural Filters 2021<br> 1892 Smart Portrait, Photoshop Neural Filters 2021<br> 1893 </span> --> 1894 1895 <h2>Student collaborators/interns</h2> 1896 I have gotten to work with some wonderful collaborators.<br> 1897 1898 <!-- <h3>Internship </h3> --> 1899<!-- <br> 1900 <font face="helvetica, ariel, 'sans serif'"> 1901 <span style="font-size: 10pt;"> 1902 If you have similar interests and are interested in collaborating during a summer 2021 internship, please feel free to contact me! Tell me about your past research experience and what you would potentially like to do. The goal of an internship is a publication, usually CVPR or SIGGRAPH. For example, see my NIPS 2017 and CVPR 2018 papers, which were from my summer 2017 internship. Interns are almost all PhD students; the number of slots is limited, so we unfortunately cannot accept everyone.<br> 1903 </span> 1904 </font> --> 1905 1906 <!-- <h3>@Adobe</h3> --> 1907 <br> 1908 <span style="font-size: 14pt;"> 1909 <img src="index_files/adobe_logo.png" alt="" style="height: 1em; vertical-align: -0.1em;"> 1910 <b>Adobe</b> 1911 </span> 1912 1913 <span style="font-size: 10pt;"> 1914 <!-- <p> --> 1915 <dl class="dl-horizontal"> 1916 <dt><b>PhD/MS [interns]</b></dt> 1917 <table border="0" cellspacing="0" cellpadding="0" style="font-size: 10pt; line-height: 1.4;" width="100%"><tbody> 1918 <tr> 1919 <td width="25%"><a href="https://shivamduggal4.github.io/">Shivam Duggal</a>, MIT</td> 1920 <td width="25%"><a href="https://graceduansu.github.io/">Grace Su</a>, CMU</td> 1921 <td width="25%"><a href="https://yossigandelsman.github.io/">Yossi Gandelsman</a>, UC Berkeley</td> 1922 <td width="25%"><a href="https://taesung.me/">Taesung Park</a>, UC Berkeley <span class="award-icon" data-tooltip="Adobe Fellowship winner, 2020"><img src="index_files/adobe_logo.png" alt=""></span></td> 1923 </tr> 1924 <tr> 1925 <td><a href="https://xingjianbai.com/">Xingjian Bai</a>, MIT</td> 1926 <td><a href="https://danielchyeh.github.io/">Chun-Hsiao (Daniel) Yeh</a>, UC Berkeley</td> 1927 <td><a href="https://yinboc.github.io/">Yinbo Chen</a>, UC San Diego</td> 1928 <td><a href="http://linji.me/">Ji Lin</a>, MIT</td> 1929 </tr> 1930 <tr> 1931 <td><a href="https://juliachae.github.io/">Julia Chae</a>, MIT</td> 1932 <td><a href="https://konpat.notion.site/">Konpat Preechakul</a>, UC Berkeley</td> 1933 <td><a href="https://nupurkmr9.github.io/">Nupur Kumari</a>, CMU</td> 1934 <td><a href="https://www.wpeebles.com/">William (Bill) Peebles</a>, UC Berkeley</td> 1935 </tr> 1936 <tr> 1937 <td><a href="https://lilydaytoy.github.io/">Wenxuan Peng</a>, Cornell</td> 1938 <td><a href="https://ryanpo.com/">Po Ryan</a>, Stanford</td> 1939 <td><a href="https://mingukkang.github.io/">Minguk Kang</a>, POSTECH</td> 1940 <td><a href="https://www.alexandonian.com/">Alex Andonian</a>, MIT</td> 1941 </tr> 1942 <tr> 1943 <td><a href="https://jespark.net/">Jeongsoo Park</a>, Cornell Tech</td> 1944 <td><a href="https://rohitgandikota.github.io/">Rohit Gandikota</a>, Northeastern</td> 1945 <td><a href="https://dave.ml/">Dave Epstein</a>, UC Berkeley</td> 1946 <td><a href="https://utkarshojha.github.io/">Utkarsh Ojha</a>, UC Davis</td> 1947 </tr> 1948 <tr> 1949 <td><a href="https://tsaishien-chen.github.io/">Tsai-Shien Chen</a>, UC Merced</td> 1950 <td><a href="https://tianweiy.github.io/">Tianwei Yin</a>, MIT</td> 1951 <td><a href="https://gauravparmar.com/">Gaurav Parmar</a>, CMU</td> 1952 <td><a href="http://arnabgho.github.io/">Arnab Ghosh</a>, Oxford</td> 1953 </tr> 1954 <tr> 1955 <td><a href="https://cfeng16.github.io/">Chao Feng</a>, Cornell Tech</td> 1956 <td><a href="https://joaanna.github.io/">Joanna Materzynska</a>, MIT</td> 1957 <td><a href="https://yotamnitzan.github.io/">Yotam Nitzan</a>, Tel Aviv University</td> 1958 <td><a href="http://minyounghuh.com/">Minyoung (Jacob) Huh</a>, MIT</td> 1959 </tr> 1960 <tr> 1961 <td>
1961<a href="https://joonghyuk.com/">Joonghyuk Shin</a>, Seoul National University</td> 1962 <td><a href="https://twizwei.github.io/">Yiran Xu</a>, UMaryland</td> 1963 <td><a href="https://homes.cs.washington.edu/~royorel/">Roy Or-El</a>, UW</td> 1964 <td><a href="https://stamarot.webgr.technion.ac.il/">Tamar Rott Shaham</a>, Technion <span class="award-icon" data-tooltip="Adobe Fellowship winner, 2020"><img src="index_files/adobe_logo.png" alt=""></span></td> 1965 </tr> 1966 <tr> 1967 <td><a href="https://1jsingh.github.io/">Jaskirat Singh</a>, Australian National University</td> 1968 <td><a href="https://alii-ganjj.github.io/">Alireza Ganjdanesh</a>, UMaryland</td> 1969 <td><a href="http://people.csail.mit.edu/lrchai/">Lucy Chai</a>, MIT <span class="award-icon" data-tooltip="Adobe Fellowship winner, 2021"><img src="index_files/adobe_logo.png" alt=""></span></td> 1970 <td><a href="https://payeah.net">Peiye Zhuang</a>, UIUC</td> 1971 </tr> 1972 <tr> 1973 <td><a href="https://sichengmo.github.io/">Sicheng Mo</a>, UCLA</td> 1974 <td><a href="https://jitengmu.github.io/">Jiteng Mu</a>, UC San Diego</td> 1975 <td><a href="https://lychenyoko.github.io/">Yuchen Liu</a>, Princeton</td> 1976 <td><a href="http://people.csail.mit.edu/smirnov/">Dima Smirnov</a>, MIT</td> 1977 </tr> 1978 <tr> 1979 <td><a href="https://xinyu-andy.github.io/">Xin (Andy) Yu</a>, University of Hong Kong</td> 1980 <td><a href="http://peterwang512.github.io/">Sheng-Yu Wang</a>, CMU</td> 1981 <td><a href="https://people.cs.umass.edu/~dliu/">Difan Liu</a>, UMass Amherst</td> 1982 <td><a href="https://www.cs.tau.ac.il/~noafish/">Noa Fish</a>, Tel Aviv</td> 1983 </tr> 1984 <tr> 1985 <td><a href="https://yibingwei-1.github.io/">Yibing Wei</a>, UWisconsin</td> 1986 <td><a href="https://jeanne-wang.github.io/">Xiaojuan Wang</a>, UWashington</td> 1987 <td></td> 1988 <td></td> 1989 </tr> 1990 </tbody></table> 1991 <br> 1992 1993 <dt><b>Masters/Undergrad [interns]</b></dt> 1994 <table border="0" cellspacing="0" cellpadding="0" style="font-size: 10pt; line-height: 1.4;" width="100%"><tbody> 1995 <tr> 1996 <td width="25%"><a href="http://people.csail.mit.edu/stevenliu/">Steven Liu</a>, MIT</td> 1997 <td width="25%"><a href="https://sjooyoo.github.io/">Seungjoo Yoo</a>, Korea Univ <span class="award-icon" data-tooltip="WIT Scholarship winner, 2019"><img src="index_files/adobe_logo.png" alt=""></span></td> 1998 <td width="25%"></td> 1999 <td width="25%"></td> 2000 </tr> 2001 </tbody></table> 2002 <br> 2003 2004 <dt><b>PhD/MS [university collaborators]</b></dt> 2005 <table border="0" cellspacing="0" cellpadding="0" style="font-size: 10pt; line-height: 1.4;" width="100%"><tbody> 2006 <tr> 2007 <td width="25%"><a href="https://stephanie-fu.github.io/">Stephanie Fu</a>, MIT</td> 2008 <td width="25%"><a href="https://netanel-tamir.github.io/">Netanel Y. Tamir</a>, Weizmann</td> 2009 <td width="25%"><a href="https://rawanmg.github.io/">Rawan Alghofaili</a>, George Mason</td> 2010 <td width="25%"><a href="http://alvinwan.com/">Alvin Wan</a>, UC Berkeley</td> 2011 </tr> 2012 <tr> 2013 <td><a href="https://ssundaram21.github.io/">Shobhita Sundaram</a>, MIT</td> 2014 <td><a href="https://www.cs.princeton.edu/~pmanocha/">Pranay Manocha</a>, Princeton</td> 2015 <td></td> 2016 <td></td> 2017 </tr> 2018 </tbody></table> 2019 <br> 2020 2021 <!-- <dt><b>Undergrad [university collaborators]</b></dt> --> 2022 <!-- <a href="http://peterwang512.github.io/">Sheng-Yu Wang</a>, UC Berkeley <br> --> 2023 </dl> 2024 2025 </span> 2026 2027 <!-- <h3>@Berkeley</h3> --> 2028 <!-- <br> -->
2029 <span style="font-size: 14pt;"> 2030 <img src="index_files/berkeley_seal.svg" alt="" style="height: 1em; vertical-align: -0.1em;"> 2031 <b>Berkeley</b> 2032 </span> 2033 2034 <span style="font-size: 10pt;"> 2035 <dl class="dl-horizontal"> 2036 <dt><b>Undergraduates</b></dt> 2037 <table border="0" cellspacing="0" cellpadding="0" style="font-size: 10pt; line-height: 1.4;" width="100%"><tbody> 2038 <tr> 2039 <td width="25%"><a href="https://www.linkedin.com/in/xin-qin-4a83b9158/">Xin Qin</a>, next @ USC</td> 2040 <td width="25%"><a href="http://www.cs.utexas.edu/~alin/">Angela S. Lin</a>, next @ UT Austin</td> 2041 <td width="25%"><a href="https://tianheyu927.github.io/">Tianhe Yu</a>, next @ Stanford</td> 2042 <td width="25%"><a href="https://www.linkedin.com/in/candrastefan/">Stefan A. Candra</a></td> 2043 </tr> 2044 <tr> 2045 <td><a href="https://www.linkedin.com/in/hemangjangle/">Hemang Jangle</a></td> 2046 <td><a href="http://young-geng.xyz/">Xinyang Geng</a>, next @ UC Berkeley</td> 2047 <td></td> 2048 <td></td> 2049 </tr> 2050 </tbody></table> 2051 </dl> 2052 2053 <!-- </p> --> 2054 </span> 2055 <!-- </p><hr size="2" align="left" noshade=""> --> 2056 2057 2058 <h2>Teaching </h2> 2059 <!-- <a href="https://research.adobe.com/fellowship/">Adobe Research Fellowship</a> 2017 --> 2060 <span style="font-size: 12pt;"> 2061 <b>Introduction to Artificial Intelligence (CS 188)</b>, UC Berkeley <br> 2062 <span style="font-size: 10pt;"> 2063 Graduate Student Instructor (GSI) with Prof. <a href="http://people.eecs.berkeley.edu/~anca/">Anca Dragan</a> <br> 2064 Spring 2017<br> 2065 <br> 2066 <span style="font-size: 12pt;"> 2067 <b>Computer Vision (CS 280)</b>, UC Berkeley <br> 2068 <span style="font-size: 10pt;"> 2069 Graduate Student Instructor (GSI) with Prof. <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, Prof. <a href="http://people.eecs.berkeley.edu/~trevor/">Trevor Darrell</a> <br> 2070 Spring 2016<br> 2071 <br> 2072 <span style="font-size: 12pt;"> 2073 <b>Introduction to Circuits (ECE 2100)</b>, Cornell University <br> 2074 <span style="font-size: 10pt;"> 2075 Teaching Assistant (TA) with Prof. <a href="https://molnargroup.ece.cornell.edu/">Alyosha Molnar</a> <br> 2076 Spring 2010<br> 2077 <br> 2078 2079 <h2>My Name</h2> 2080 Confused by the contents of this page? Well, you may have been looking for Professor <a href="https://www.cs.sfu.ca/~haoz/" border="0">Richard Zhang</a> or Professor <a href="https://ryz.ece.illinois.edu/" border="0">Richard Zhang</a>. My Chinese name is ç« ç¿å. 2081
2082<script>
vendor: 339 bytes, lines 2082-2088
2082 2083 (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ 2084 (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), 2085 m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) 2086 })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); 2087 2088 ga('create', '
2088UA-75897335-1
vendor: 38 bytes, lines 2088-2089
2088', 'auto'); 2089 ga('send', 'pageview');
2090</script>
2090 2091 2092</font> 2093</td></tr></tbody></table> 2094</body> 2095</html> 2096 2097
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.