1<!DOCTYPE html> 2<html> 3 4<head> 5 <!-- <meta http-equiv="refresh" content="0;url=http://graduatestudents.ucmerced.edu/wlai24/" /> --> 6 <meta charset='utf-8'> 7 <meta http-equiv="X-UA-Compatible" content="chrome=1"> 8 <meta name="description" content="kpzhang93.github.io : "> 9 <meta name="viewport" content="width=device-width, initial-scale=1.0"> 10 <meta name="author" content="Shuhuai Ren"> 11 <link rel="stylesheet" href="./src/main.css"> 12 <link rel="stylesheet" href="./src/bootstrap.min.css"> 13 <link rel="stylesheet" href="./src/bootstrap-theme.min.css"> 14 15 <link rel="stylesheet" href="http://netdna.bootstrapcdn.com/font-awesome/4.4.0/css/font-awesome.min.css"> 16 17 18 <link rel="stylesheet" href="./src/bootstrap-navbar-custom.css"> 19 <link rel="stylesheet" href="./src/scrolling-nav.css"> 20 <link rel="stylesheet" href="./src/mfp.css"> 21 22 <link rel="shortcut icon" href="./src/Jamie.jpg"> 23 24
24<script async="" src="./src/analytics.js"></script>
24 25
25<script>
vendor: 514 bytes, lines 25-38
25 26 (function (i, s, o, g, r, a, m) { 27 i['GoogleAnalyticsObject'] = r; 28 i[r] = i[r] || function () { 29 (i[r].q = i[r].q || []).push(arguments) 30 }, i[r].l = 1 * new Date(); 31 a = s.createElement(o), 32 m = s.getElementsByTagName(o)[0]; 33 a.async = 1; 34 a.src = g; 35 m.parentNode.insertBefore(a, m) 36 })(window, document, 'script', '//www.google-analytics.com/analytics.js', 'ga'); 37 38 ga('create', '
38UA-45156688-2
vendor: 48 bytes, lines 38-40
38', 'auto'); 39 ga('send', 'pageview'); 40
40</script>
40 41 42 <title>Shuhuai Ren</title> 43</head> 44 45<body id="page-top" data-spy="scroll" data-target=".navbar-fixed-top">
46<script async defer src="https://buttons.github.io/buttons.js"></script>
46 47<!-- HEADER --> 48 49 50<section id="publication" class="publication-section"> 51 <div class="container"> 52 <h2>Publications (*Equal Contribution)</h2> 53 <hr> 54 55 <h3>2025</h3> 56 <hr> 57 58 <div class="spacer"></div> 59 <div class="row item"> 60 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 61 <a class="image-popup-no-margins" href="./papers/mimo.png"> 62 <img src="./papers/mimo.png" class="img-thumbnail img-responsive"> 63 </a> 64 </div> 65 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 66 <div class="paper"> MiMo-VL Technical Report</div> 67 <div class="author"><b>Shuhuai Ren (Core Contributor)</b>, et al 68 </div> 69 70 <div class="conf">Arxiv 2025</div> 71 <div class="tag"> 72 <span class="label label-default">Arxiv</span> 73 </div> 74 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2506.03569" target="blank">Paper</a> 75 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/XiaomiMiMo/MiMo-VL" target="blank">Code& 76 Model</a> 77 </div> 78 </div> 79 80 <div class="spacer"></div> 81 <div class="row item"> 82 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 83 <a class="image-popup-no-margins" href="./papers/tokenbridge.svg"> 84 <img src="./papers/tokenbridge.svg" class="img-thumbnail img-responsive"> 85 </a> 86 </div> 87 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 88 <div class="paper"> TokenBridge: Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation 89 </div> 90 <div class="author">Yuqing Wang, Zhijie Lin, Yao Teng, Yuanzhi Zhu, <b>Shuhuai Ren</b>, Jiashi Feng, Xihui Liu</div> 91 <div class="conf">ICCV 2025</div> 92 <div class="tag"> 93 <span class="label label-success">Conference</span> 94 </div> 95 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2503.16430" 96 target="blank">Paper</a> 97 <i class="fa fa fa-file-text fa-fw"></i><a href="https://yuqingwang1029.github.io/TokenBridge/" target="blank">Code& 98 Model</a> 99 </div> 100 </div> 101 102 <div class="spacer"></div> 103 <div class="row item"> 104 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 105 <a class="image-popup-no-margins" href="./papers/par.jpg"> 106 <img src="./papers/nbp.png" class="img-thumbnail img-responsive"> 107 </a> 108 </div> 109 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 110 <div class="paper"> Next Block Prediction: Video Generation via Semi-Autoregressive Modeling 111 </div> 112 <div class="author"><b>Shuhuai Ren</b>, Shuming Ma, Xu Sun, Furu Wei</div> 113 <div class="conf">Arxiv 2025</div> 114 <div class="tag"> 115 <span class="label label-default">Arxiv</span> 116 </div> 117 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2502.07737" 118 target="blank">Paper</a> 119 <i class="fa fa fa-file-text fa-fw"></i><a href="https://renshuhuai-andy.github.io/NBP-project/" target="blank">Code& 120 Model</a> 121 </div> 122 </div> 123 124 <h3>2024</h3> 125 <hr> 126 127 <div class="spacer"></div> 128 <div class="row item"> 129 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 130 <a class="image-popup-no-margins" href="./papers/ntp_survey.png"> 131 <img src="./papers/ntp_survey.png" class="img-thumbnail img-responsive"> 132 </a> 133 </div> 134 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 135 <div class="paper"> Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey 136 </div> 137 <div class="author">Liang Chen, Zekun Wang, <b>Shuhuai Ren</b>, Lei Li, Haozhe Zhao, Yunshui Li, Zefan Cai, Hongcheng Guo, Lei Zhang, Yizhe Xiong, Yichi Zhang, Ruoyu Wu, Qingxiu Dong, Ge Zhang, Jian Yang, Lingwei Meng, Shujie Hu, Yulong Chen, Junyang Lin, Shuai Bai, Andreas Vlach
137os, Xu Tan, Minjia Zhang, Wen Xiao, Aaron Yee, Tianyu Liu, Baobao Chang</div> 138 <div class="conf">Arxiv 2024</div> 139 <div class="tag"> 140 <span class="label label-default">Arxiv</span> 141 </div> 142 <i class="fa fa-book fa-fw"></i><a href="https://www.arxiv.org/abs/2412.18619" 143 target="blank">Paper</a> 144 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/LMM101/Awesome-Multimodal-Next-Token-Prediction" target="blank">Code& 145 Model</a> 146 </div> 147 </div> 148 149 <div class="spacer"></div> 150 <div class="row item"> 151 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 152 <a class="image-popup-no-margins" href="./papers/par.jpg"> 153 <img src="./papers/par.jpg" class="img-thumbnail img-responsive"> 154 </a> 155 </div> 156 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 157 <div class="paper"> Parallelized Autoregressive Visual Generation 158 </div> 159 <div class="author">Yuqing Wang, <b>Shuhuai Ren</b>, Zhijie Lin, Yujin Han, Haoyuan Guo, Zhenheng Yang, Difan Zou, Jiashi Feng, Xihui Liu</div> 160 <div class="conf">CVPR 2025 (Highlights)</div> 161 <div class="tag"> 162 <span class="label label-success">Conference</span> 163 </div> 164 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2412.15119" 165 target="blank">Paper</a> 166 <i class="fa fa fa-file-text fa-fw"></i><a href="https://epiphqny.github.io/PAR-project/" target="blank">Code& 167 Model</a> 168 </div> 169 </div> 170 171 <div class="spacer"></div> 172 <div class="row item"> 173 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 174 <a class="image-popup-no-margins" href="./papers/video-mme.png"> 175 <img src="./papers/video-mme.png" class="img-thumbnail img-responsive"> 176 </a> 177 </div> 178 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 179 <div class="paper">Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis</div> 180 <div class="author">Chaoyou Fu, Yuhan Dai, Yondong Luo, Lei Li, <b>Shuhuai Ren</b>, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, Peixian Chen, Yanwei Li, Shaohui Lin, Sirui Zhao, Ke Li, Tong Xu, Xiawu Zheng, Enhong Chen, Rongrong Ji, Xing Sun 181 </div> 182 183 <!-- (* indicates equal contribution) --> 184 <div class="conf">CVPR 2025 (Highlights)</div> 185 <div class="tag"> 186 <span class="label label-success">Conference</span> 187 </div> 188 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2405.21075" target="blank">Paper</a> 189 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/BradyFU/Video-MME" target="blank">Code& 190 Model</a> 191 </div> 192 </div> 193 194 <div class="spacer"></div> 195 <div class="row item"> 196 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 197 <a class="image-popup-no-margins" href="./papers/LaDiC.png"> 198 <img src="./papers/LaDiC.png" class="img-thumbnail img-responsive"> 199 </a> 200 </div> 201 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 202 <div class="paper"> LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?</div> 203 <div class="author">Yuchi Wang*, <b>Shuhuai Ren</b>*, Rundong Gao, Linli Yao, Qingyan Guo, Kaikai An, Jianhong Bai, Xu Sun 204 </div> 205 206 <!-- (* indicates equal contribution) --> 207 <div class="conf">NAACL 2024</div> 208 <div class="tag">
209 <span class="label label-success">Conference</span> 210 </div> 211 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2404.10763" target="blank">Paper</a> 212 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/wangyuchi369/LaDiC" target="blank">Code& 213 Model</a> 214 </div> 215 </div> 216 217 <div class="spacer"></div> 218 <div class="row item"> 219 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 220 <a class="image-popup-no-margins" href="./papers/VITATECS.png"> 221 <img src="./papers/VITATECS.png" class="img-thumbnail img-responsive"> 222 </a> 223 </div> 224 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 225 <div class="paper"> VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models</div> 226 <div class="author">Shicheng Li, Lei Li, <b>Shuhuai Ren</b>, Yuanxin Liu, Yi Liu, Rundong Gao, Xu Sun, Lu Hou 227 </div> 228 229 <!-- (* indicates equal contribution) --> 230 <div class="conf">ECCV 2024</div> 231 <div class="tag"> 232 <span class="label label-success">Conference</span> 233 </div> 234 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2311.17404" target="blank">Paper</a> 235 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lscpku/VITATECS" target="blank">Code& 236 Model</a> 237 </div> 238 </div> 239 240 <div class="spacer"></div> 241 <div class="row item"> 242 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 243 <a class="image-popup-no-margins" href="./papers/TempCompass.png"> 244 <img src="./papers/TempCompass.png" class="img-thumbnail img-responsive"> 245 </a> 246 </div> 247 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 248 <div class="paper"> TempCompass: Do Video LLMs Really Understand Videos?</div> 249 <div class="author">Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, <b>Shuhuai Ren</b>, Lei Li, Sishuo Chen, Xu Sun, Lu Hou 250 </div> 251 252 <!-- (* indicates equal contribution) --> 253 <div class="conf">Findings of ACL 2024 (Long Paper)</div> 254 <div class="tag"> 255 <span class="label label-success">Conference</span> 256 </div> 257 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2403.00476" target="blank">Paper</a> 258 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/llyx97/TempCompass" target="blank">Code& 259 Model</a> 260 </div> 261 </div> 262 263 <div class="spacer"></div> 264 <div class="row item"> 265 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 266 <a class="image-popup-no-margins" href="./papers/pca-bench.png"> 267 <img src="./papers/pca-bench.png" class="img-thumbnail img-responsive"> 268 </a> 269 </div> 270 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 271 <div class="paper"> PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain</div> 272 <div class="author">Liang Chen, Yichi Zhang, <b>Shuhuai Ren</b>, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang 273 </div> 274 275 <!-- (* indicates equal contribution) --> 276 <div class="conf">Findings of ACL 2024 (Long Paper)</div> 277 <div class="tag"> 278 <span class="label label-success">Conference</span> 279 </div> 280 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2402.15527" target="blank">Paper</a> 281 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/pkunlp-icler/PCA-EVAL" target="blank">Code& 282 Model</a> 283 </div> 284 </div> 285 286 <div class="spacer"></div> 287 <div class="row item"> 288 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 289 <a class="image-popup-no-margins" href="./papers/MR-VPC.png"> 290 <img src="./papers/MR-VPC.png" class="img-thumbnail img-responsive"> 291 </a> 292 </div> 293 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 294 <div class="paper"> Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality</div> 295 <div class="author">Sishuo Chen, Lei Li, <b>Shuhuai Ren</b>, Rundong Gao, Yuanxin Liu, Xiaohan Bi, Xu Sun, Lu Hou 296 </div> 297 298 <!-- (* indicates equal contribution) --> 299 <div class="conf">Arxiv 2024</div> 300 <div class="tag">
301 <span class="label label-default">Arxiv</span> 302 </div> 303 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2403.19221" target="blank">Paper</a> 304 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lancopku/MR-VPC" target="blank">Code& 305 Model</a> 306 </div> 307 </div> 308 309 <h3>2023</h3> 310 <hr> 311 312 <div class="spacer"></div> 313 <div class="row item"> 314 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 315 <a class="image-popup-no-margins" href="./papers/timechat.png"> 316 <img src="./papers/timechat.png" class="img-thumbnail img-responsive"> 317 </a> 318 </div> 319 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 320 <div class="paper"> TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding</div> 321 <div class="author"><b>Shuhuai Ren</b>*, Linli Yao*, Shicheng Li, Xu Sun, Lu Hou 322 </div> 323 324 <!-- (* indicates equal contribution) --> 325 <div class="conf">CVPR 2024</div> 326 <div class="tag"> 327 <span class="label label-success">Conference</span> 328 </div> 329 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2312.02051" target="blank">Paper</a> 330 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/RenShuhuai-Andy/TimeChat" target="blank">Code& 331 Model</a> 332 </div> 333 </div> 334 335 <div class="spacer"></div> 336 <div class="row item"> 337 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 338 <a class="image-popup-no-margins" href="./papers/testa.png"> 339 <img src="./papers/testa.png" class="img-thumbnail img-responsive"> 340 </a> 341 </div> 342 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 343 <div class="paper"> TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding</div> 344 <div class="author"><b>Shuhuai Ren</b>, Sishuo Chen, Shicheng Li, Xu Sun, Lu Hou 345 </div> 346 347 <!-- (* indicates equal contribution) --> 348 <div class="conf">Findings of EMNLP 2023 (Long Paper)</div> 349 <div class="tag"> 350 <span class="label label-success">Conference</span> 351 </div> 352 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2310.19060" target="blank">Paper</a> 353 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/RenShuhuai-Andy/TESTA" target="blank">Code& 354 Model</a> 355 </div> 356 </div> 357 358 <div class="spacer"></div> 359 <div class="row item"> 360 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 361 <a class="image-popup-no-margins" href="./papers/pomp.png"> 362 <img src="./papers/pomp.png" class="img-thumbnail img-responsive"> 363 </a> 364 </div> 365 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 366 <div class="paper"> Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition</div> 367 <div class="author"><b>Shuhuai Ren</b>, Aston Zhang, Yi Zhu, Shuai Zhang, Shuai Zheng, Mu Li, Alex Smola, Xu Sun 368 </div> 369 370 <!-- (* indicates equal contribution) --> 371 <div class="conf">NeurIPS 2023</div> 372 <div class="tag"> 373 <span class="label label-success">Conference</span> 374 </div> 375 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2304.04704" target="blank">Paper</a> 376 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/amazon-science/prompt-pretraining" target="blank">Code& 377 Model</a> 378 </div> 379 </div> 380 381 <div class="spacer"></div> 382 <div class="row item"> 383 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 384 <a class="image-popup-no-margins" href="./papers/fetv.png"> 385 <img src="./papers/fetv.png" class="img-thumbnail img-responsive"> 386 </a> 387 </div> 388 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 389 <div class="paper"> FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation</div> 390 <div class="author">Yuanxin Liu, Lei Li, <b>Shuhuai Ren</b>, Rundong Gao, Shicheng Li, Sishuo Chen, Xu Sun, Lu Hou 391 </div> 392 393 <!-- (* indicates equal contribution) --> 394 <div class="conf">NeurIPS 2023 (Dataset & Benchmark Track)</div> 395 <div class="tag">
396 <span class="label label-success">Conference</span> 397 </div> 398 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2311.01813" target="blank">Paper</a> 399 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/llyx97/FETV" target="blank">Code& 400 Model</a> 401 </div> 402 </div> 403 404<!-- <div class="spacer"></div>--> 405<!-- <div class="row item">--> 406<!-- <div class="col-md-4 col-sm-6 col-xs-12 item-img">--> 407<!-- <a class="image-popup-no-margins" href="./papers/pca_eval.png">--> 408<!-- <img src="./papers/pca_eval.png" class="img-thumbnail img-responsive">--> 409<!-- </a>--> 410<!-- </div>--> 411<!-- <div class="col-md-8 col-sm-6 col-xs-12 item-info">--> 412<!-- <div class="paper"> Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond</div>--> 413<!-- <div class="author">Liang Chen, Yichi Zhang, <b>Shuhuai Ren</b>, Haozhe Zhao, Zefan Cai, Yuchi Wang, Tianyu Liu, Baobao Chang--> 414<!-- </div>--> 415 416<!-- <!– (* indicates equal contribution) –>--> 417<!-- <div class="conf">NeurIPS 2023 Foundation Models for Decision Making Workshop</div>--> 418<!-- <div class="tag">--> 419<!-- <span class="label label-default">Workshop</span>--> 420<!-- </div>--> 421<!-- <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2310.02071" target="blank">Paper</a>--> 422<!-- <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/pkunlp-icler/PCA-EVAL" target="blank">Code&--> 423<!-- Model</a>--> 424<!-- </div>--> 425<!-- </div>--> 426 427 <div class="spacer"></div> 428 <div class="row item"> 429 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 430 <a class="image-popup-no-margins" href="./papers/m3it.png"> 431 <img src="./papers/m3it.png" class="img-thumbnail img-responsive"> 432 </a> 433 </div> 434 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 435 <div class="paper"> M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning</div> 436 <div class="author">Lei Li, Yuwei Yin, Shicheng Li, Liang Chen, Peiyi Wang, <b>Shuhuai Ren</b>, Mukai Li, Yazheng Yang, Jingjing Xu, Xu Sun, Lingpeng Kong, Qi Liu 437 </div> 438 439 <!-- (* indicates equal contribution) --> 440 <div class="conf">Arxiv 2023</div> 441 <div class="tag"> 442 <span class="label label-default">Arxiv</span> 443 </div> 444 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2306.04387" target="blank">Paper</a> 445 <i class="fa fa fa-file-text fa-fw"></i><a href="https://huggingface.co/papers/2306.04387" target="blank">Dataset</a> 446 </div> 447 </div> 448 449 <h3>2022</h3> 450 <hr> 451 452 <div class="spacer"></div> 453 <div class="row item"> 454 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 455 <a class="image-popup-no-margins" href="./papers/openness.png"> 456 <img src="./papers/openness.png" class="img-thumbnail img-responsive"> 457 </a> 458 </div> 459 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 460 <div class="paper"> Delving into the Openness of CLIP</div> 461 <div class="author"><b>Shuhuai Ren</b>, Lei Li, Xuancheng Ren, Guangxiang Zhao, Xu Sun 462 </div> 463 464 <!-- (* indicates equal contribution) --> 465 <div class="conf">Findings of ACL 2023 (Long Paper)</div> 466 <div class="tag"> 467 <span class="label label-success">Conference</span> 468 </div> 469 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2206.01986" target="blank">Paper</a> 470 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lancopku/clip-openness" target="blank">Code& 471 Model</a> 472 </div> 473 </div> 474 475 <h3>2021</h3> 476 <hr> 477 478 <div class="spacer"></div> 479 <div class="row item"> 480 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 481 <a class="image-popup-no-margins" href="./papers/cuge.png"> 482 <img src="./papers/cuge.png" class="img-thumbnail img-responsive"> 483 </a> 484 </div> 485 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 486 <div class="paper">CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark</div> 487<!-- <div class="author">Yuan Yao, ..., <b>Shuhuai Ren</b>, ..., Zhiyuan Liuâ, Xianpei Hanâ, Erhong Yangâ, Zhifang Suiâ, Maosong Sunâ--> 488 <div class="author">Yuan Yao, Qingxiu Dong, Jian Guan, Boxi Cao, Zhengyan Zhang, Chaojun Xiao, Xiaozhi Wang, Fanchao Qi, Junwei Bao, Jinran Nie, Zheni Zeng, Yuxian Gu, Kun Zhou, Xuancheng Huang, Wenhao Li, <b>Shuhuai Ren</b>, Jinliang Lu, Chengqiang Xu, Huadong Wang, Guoyang Zeng, Zile Zhou, Jiajun Zhang, Juanzi Li, Minlie Huang, Rui Yan, Xiaodong He, Xiaojun Wan, Xin Zhao, Xu Sun, Yang Liu, Zhiyuan Liuâ, Xianpei Hanâ, Erhong Yangâ, Zhifang Suiâ, Maosong Sunâ 489 </div> 490 491 <!-- (* indicates equal contribution) --> 492 <div class="tag">
493 <span class="label label-default">Preprint</span> 494 </div> 495 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2112.13610" target="blank">Paper</a> 496 <i class="fa fa fa-file-text fa-fw"></i><a href="http://cuge.baai.ac.cn/#/" target="blank">Benchmark</a> 497 </div> 498 </div> 499 500 <div class="spacer"></div> 501 <div class="row item"> 502 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 503 <a class="image-popup-no-margins" href="./papers/taa.png"> 504 <img src="./papers/taa.png" class="img-thumbnail img-responsive"> 505 </a> 506 </div> 507 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 508 <div class="paper"> Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification</div> 509 <div class="author"><b>Shuhuai Ren</b>, Jinchao Zhang, Lei li, Xu Sun*, Jie Zhou 510 </div> 511 512 <!-- (* indicates equal contribution) --> 513 <div class="conf">EMNLP 2021 (Long Paper)</div> 514 <div class="tag"> 515 <span class="label label-success">Conference</span> 516 </div> 517 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2109.00523" target="blank">Paper</a> 518 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lancopku/text-autoaugment" target="blank">Code& 519 Model</a> 520 </div> 521 </div> 522 523 <div class="spacer"></div> 524 <div class="row item"> 525 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 526 <a class="image-popup-no-margins" href="./papers/dkd.png"> 527 <img src="./papers/dkd.png" class="img-thumbnail img-responsive"> 528 </a> 529 </div> 530 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 531 <div class="paper"> Dynamic Knowledge Distillation for Pre-trained Language Models</div> 532 <div class="author">Lei Li, Yankai Lin, <b>Shuhuai Ren</b>, Peng Li, Jie Zhou, Xu Sun* 533 </div> 534 535 <!-- (* indicates equal contribution) --> 536 <div class="conf">EMNLP 2021 (Long Paper, <span style="color:#FF0000;font-weight:bold;">Oral</span>)</div> 537 <div class="tag"> 538 <span class="label label-success">Conference</span> 539 </div> 540 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2109.11295" target="blank">Paper</a> 541 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lancopku/DynamicKD" target="blank">Code& 542 Model</a> 543 </div> 544 </div> 545 546 <div class="spacer"></div> 547 <div class="row item"> 548 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 549 <a class="image-popup-no-margins" href="./papers/cascadebert.png"> 550 <img src="./papers/cascadebert.png" class="img-thumbnail img-responsive"> 551 </a> 552 </div> 553 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 554 <div class="paper"> CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade </div> 555 <div class="author">Lei Li, Yankai Lin, Deli Chen, <b>Shuhuai Ren</b>, Peng Li, Jie Zhou, Xu Sun* 556 </div> 557 558 <!-- (* indicates equal contribution) --> 559 <div class="conf">Findings of EMNLP 2021 (Long Paper)</div> 560 <div class="tag"> 561 <span class="label label-success">Conference</span> 562 </div> 563 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2012.14682" target="blank">Paper</a> 564 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lancopku/CascadeBERT" target="blank">Code& 565 Model</a> 566 </div> 567 </div> 568 569 <div class="spacer"></div> 570 <div class="row item"> 571 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 572 <a class="image-popup-no-margins" href="./papers/iais_case.png"> 573 <img src="./papers/iais_case.png" class="img-thumbnail img-responsive"> 574 </a> 575 </div> 576 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 577 <div class="paper"> Learning Relation Alignment for Calibrated Cross-modal Retrieval</div> 578 <div class="author"><b>Shuhuai Ren</b>, Junyang Lin, Guangxiang Zhao, Rui Men, An Yang, Jingren Zhou, Xu Sun*, Hongxia 579 Yang 580 </div> 581 582 <!-- (* indicates equal contribution) --> 583 <div class="conf">ACL 2021 (Long Paper, <span style="color:#FF0000;font-weight:bold;">Oral</span>)</div> 584 <div class="tag">
585 <span class="label label-success">Conference</span> 586 </div> 587 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/2105.13868" target="blank">Paper</a> 588 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/lancopku/IAIS" target="blank">Code& 589 Model</a> 590 </div> 591 </div> 592 593 <h3>2020</h3> 594 <hr> 595 596 <div class="spacer"></div> 597 <div class="row item"> 598 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 599 <a class="image-popup-no-margins" href="./papers/dca.png"> 600 <img src="./papers/dca.png" class="img-thumbnail img-responsive"> 601 </a> 602 </div> 603 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 604 <div class="paper">DCA: Diversified Co-Attention towards Informative Live Video Commenting</div> 605 <div class="author">Zhihan Zhang, Zhiyi Yin, <b>Shuhuai Ren</b>, Xinhang Li, Shicheng Li</div> 606 <div class="conf">NLPCC 2020 (Long Paper)</div> 607 <div class="tag"> 608 <span class="label label-success">Conference</span> 609 </div> 610 <i class="fa fa-book fa-fw"></i><a href="https://arxiv.org/abs/1911.02739" target="blank">Paper</a> 611 </div> 612 </div> 613 614 <h3>2019</h3> 615 <hr> 616 617 <div class="spacer"></div> 618 <div class="row item"> 619 <div class="col-md-4 col-sm-6 col-xs-12 item-img"> 620 <a class="image-popup-no-margins" href="./papers/pwws.png"> 621 <img src="./papers/pwws.png" class="img-thumbnail img-responsive"> 622 </a> 623 </div> 624 <div class="col-md-8 col-sm-6 col-xs-12 item-info"> 625 <div class="paper"> Generating Natural Language Adversarial Examples through Probability Weighted Word 626 Saliency 627 </div> 628 <div class="author"><b>Shuhuai Ren</b>, Yihe Deng, Kun He*, Wangxiang Che</div> 629 <div class="conf">ACL 2019 (Long Paper, <span style="color:#FF0000;font-weight:bold;">Oral</span>)</div> 630 <div class="tag"> 631 <span class="label label-success">Conference</span> 632 </div> 633 <i class="fa fa-book fa-fw"></i><a href="https://www.aclweb.org/anthology/P19-1103" 634 target="blank">Paper</a> 635 <i class="fa fa fa-file-text fa-fw"></i><a href="https://github.com/JHL-HUST/PWWS" target="blank">Code& 636 Model</a> 637 </div> 638 </div> 639 <br> 640 <br> 641 642 </div> <!-- end of Publication --> 643 644</section> 645 646 647</div></section> 648 649 650<div class="footer"> 651 <div class="container"> 652 <div class="row item"> 653 <p align="center"><a href='https://clustrmaps.com/site/1bjja' title='Visit tracker'><img 654 src='//clustrmaps.com/map_v2.png?cl=ffffff&w=a&t=tt&d=PgzBKvDwV0_11OsfeUcddl13pJ1ccAn3Or6O6qYWHuM&co=2d78ad&ct=ffffff'/></a> 655 </p> 656 <div>Copyright © Shuhuai Ren 2021</div> 657 <div>Template from <a href="http://phoenix104104.github.io">Jason Lai</a></div> 658 <div class="last-update"> 659 Last Updated: 660
660<script language="JavaScript"> 661 document.write(document.lastModified); 662 </script>
662 663 </div> 664 <!-- <div align="center"><a href="http://www.amazingcounters.com"><img src="http://cc.amazingcounters.com/counter.php?i=3246736&c=9740521"--> 665 <!-- alt="AmazingCounters.com"></a></div>--> 666 </div> 667 668 </div> 669 670
670<script type="text/javascript" src="./src/jquery-1.11.0.js"></script>
670 671
671<script src="./src/bootstrap.min.js"></script>
671 672 <!-- 673
673<script src="//code.jquery.com/jquery-1.11.3.min.js"></script>
673 674
674<script src="//code.jquery.com/jquery-migrate-1.2.1.min.js"></script>
674 675
675<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.5/js/bootstrap.min.js"></script>
675 676 --> 677 <!-- Scrolling Nav JavaScript --> 678
678<script src="./src/jquery.easing.min.js"></script>
678 679
679<script src="./src/scrolling-nav.js"></script>
679 680
680<script src="./src/mfp.js"></script>
680 681
681<script type="text/javascript" src="./src/main.js"></script>
681 682 683 684</div> 685 686</body> 687</html>
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.