PageSourceSearch

https://lin-shan.com/

html lin-shan.com collected 2026-09-28 07:11:26 UTC 11,702 bytes, 305 lines download raw bytes

1<!DOCTYPE html>
2<html lang="en-US">
3  <head>
4    <title>Chubin Zhang | Tsinghua University</title>
5
6    <meta charset="UTF-8">
7    <meta http-equiv="X-UA-Compatible" content="IE=edge">
8    <meta name="viewport" content="width=device-width, initial-scale=1">
9    <meta name="description" content="Homepage of Chubin Zhang">
10    
11    <meta name="keywords" content="Chubin Zhang 张楚斌 GeoLRM OccNeRF">
12    
13    
14    <link rel="canonical" href="https://linshan-bin.github.io/"/>
15    
16
17    <link rel="icon" media="(prefers-color-scheme:dark)" href="./assets/img/favicon.png" type="image/png" />
18    <link rel="icon" media="(prefers-color-scheme:light)" href="./assets/img/favicon.png" type="image/png" />
19    
19<script src="./assets/js/favicon-switcher.js" type="application/javascript"></script>
19
20
21    <link rel=stylesheet href=https://cdnjs.cloudflare.com/ajax/libs/academicons/1.8.6/css/academicons.min.css integrity="sha256-uFVgMKfistnJAfoCUQigIl+JfUaP47GrRKjf6CTPVmw=" crossorigin=anonymous>
22    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/all.min.css" integrity="sha512-z3gLpd7yknf1YoNbCzqRKc4qyor8gaKU1qmn+CShxbuBusANI9QpRohGBreCFkKxLhei6S9CQXFEbbKuqLg0DA==" crossorigin="anonymous" referrerpolicy="no-referrer" />
23    
24    
25    <link rel="stylesheet" href="./assets/css/font_sans_serif.css">
26    
27    
28    <link rel="stylesheet" href="./assets/css/style.css">
29    <link rel="stylesheet" href="./assets/css/publications.css">
30    
31
32  </head>
33  <body>
34    <div class="wrapper">
35      <header>
36        
37        
38        <a class="image avatar"><img src="./assets/img/avatar.jpg" alt="avatar" /></a>
39        
40
41        <h1>Chubin Zhang</h1>
42
43        
44        <position style="font-size:1.10rem;">Ph.D. Student</position>
45        <br>
46        
47        
48        <a href="" rel="noopener"><autocolor>Tsinghua University</autocolor></a>
49        <br>
50        
51        
52        <email>zcb24 (at) mails.tsinghua.edu.cn</email>
53        
54
55        <br>
56        <br>
57        <div class="social-icons">
58        
59        <a style="margin: 0 5px 0 0" href="https://scholar.google.com/citations?user=etopZM4AAAAJ">
60          <i class="ai ai-google-scholar" style="font-size:1.2rem"></i>
61        </a>  
62        
63
64        
65
66        
67        <a style="margin: 0 5px 0 0" href="https://github.com/LinShan-Bin">
68          <i class="fab fa-github"></i>
69        </a>
70        
71
72        
73
74        
75        </div>
76        <br>
77
78      </header>
79      <section>
80
81      <h2 id="about-me">About Me</h2>
82
83<p>I’m currently a second-year Ph.D. student at Tsinghua Shenzhen International Graduate School, supervised by Prof. <a href="https://andytang15.github.io/">Yansong Tang</a> and Prof. <a href="https://ivg.au.tsinghua.edu.cn/Jiwen_Lu/">Jiwen Lu</a>. My recent research focuses on 3D vision and its intersection with Robotics and AIGC.</p>
84
85<p>Prior to my PhD, I received a bachelor from the <a href="https://www.au.tsinghua.edu.cn/en/">Department of Automation</a>, <a href="https://www.tsinghua.edu.cn/en/">Tsinghua University</a>. I am also a member of Class of General Artificial Intelligence of Tsinghua University. In my undergraduate research, I am fortunate to work with <a href="https://duanyueqi.github.io/">Yueqi Duan</a> at the Department of Electronic Engineering of Tsinghua University. We have great collaborations working on 3D reconstruction.</p>
86
87<h2 id="publications" style="margin: 2px 0px -15px;">Publications</h2>
88
89<div class="publications">
90<ol class="bibliography">
91
92
93
94<li>
95<div class="pub-row">
96  <div class="col-sm-3 abbr" style="position: relative;padding-right: 15px;padding-left: 15px;">
97     
98    <img src="./assets/img/teaser_CLAP.png" class="teaser img-fluid z-depth-1" style="width=100;height=40%" />
99     
100    <abbr class="badge">Preprint</abbr>
101    
102    
103  </div>
104  <div class="col-sm-9" style="position: relative;padding-right: 15px;padding-left: 20px;">
105      <div class="title"><a href="https://arxiv.org/pdf/2601.04061">CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos</a></div>
106      <div class="author"><strong>Chubin Zhang</strong>, Jianan Wang, Zifeng Gao, Yue Su, Tianru Dai, Cai Zhou, Jiwen Lu, Yansong Tang</div>
107      <div class="periodical"><em>Preprint</em>
108      </div>
109    <div class="links">
110       
111      <a href="https://arxiv.org/pdf/2601.04061" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">PDF</a>
112      
113       
114      <a href="https://github.com/LinShan-Bin/OpenCLAP" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">
114Code</a>
115      
116       
117      <a href="https://lin-shan.com/CLAP/" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">Page</a>
118      
119       
120      <a href="https://arxiv.org/abs/2601.04061" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">arXiv</a>
121      
122      
123      
124      
125    </div>
126  </div>
127</div>
128</li>
129<br />
130
131
132
133<li>
134<div class="pub-row">
135  <div class="col-sm-3 abbr" style="position: relative;padding-right: 15px;padding-left: 15px;">
136     
137    <img src="./assets/img/teaser_vlarl.png" class="teaser img-fluid z-depth-1" style="width=100;height=40%" />
138     
139    <abbr class="badge">Preprint</abbr>
140    
141    
142  </div>
143  <div class="col-sm-9" style="position: relative;padding-right: 15px;padding-left: 20px;">
144      <div class="title"><a href="https://arxiv.org/pdf/2505.18719">VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning</a></div>
145      <div class="author">Guanxing Lu, Wenkai Guo, <strong>Chubin Zhang</strong>, Yuheng Zhou, Haonan Jiang, Zifeng Gao, Yansong Tang, Ziwei Wang</div>
146      <div class="periodical"><em>Preprint</em>
147      </div>
148    <div class="links">
149       
150      <a href="https://arxiv.org/pdf/2505.18719" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">PDF</a>
151      
152       
153      <a href="https://github.com/GuanxingLu/vlarl" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">
153Code</a>
154      
155      
156       
157      <a href="https://arxiv.org/abs/2505.18719" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">arXiv</a>
158      
159      
160      
161      
162    </div>
163  </div>
164</div>
165</li>
166<br />
167
168
169
170<li>
171<div class="pub-row">
172  <div class="col-sm-3 abbr" style="position: relative;padding-right: 15px;padding-left: 15px;">
173     
174    <img src="./assets/img/teaser_geolrm.png" class="teaser img-fluid z-depth-1" style="width=100;height=40%" />
175     
176    <abbr class="badge">NeurIPS</abbr>
177    
178    
179  </div>
180  <div class="col-sm-9" style="position: relative;padding-right: 15px;padding-left: 20px;">
181      <div class="title"><a href="https://proceedings.neurips.cc/paper_files/paper/2024/file/6506964d22ede4d36adae956e6a9919a-Paper-Conference.pdf">GeoLRM: Geometry-aware Large Reconstruction Model for High-quality 3D Gaussian Generation</a></div>
182      <div class="author"><strong>Chubin Zhang</strong>, Hongliang Song, Yi Wei, Chen Yu, Jiwen Lu, Yansong Tang* (*Corresponding authors)</div>
183      <div class="periodical"><em>The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)</em>
184      </div>
185    <div class="links">
186       
187      <a href="https://proceedings.neurips.cc/paper_files/paper/2024/file/6506964d22ede4d36adae956e6a9919a-Paper-Conference.pdf" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">PDF</a>
188      
189       
190      <a href="https://github.com/alibaba-yuanjing-aigclab/GeoLRM" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">
190Code</a>
191      
192       
193      <a href="https://lin-shan.com/GeoLRM/" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">Page</a>
194      
195       
196      <a href="https://arxiv.org/abs/2406.15333" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">arXiv</a>
197      
198      
199      
200      
201    </div>
202  </div>
203</div>
204</li>
205<br />
206
207
208
209<li>
210<div class="pub-row">
211  <div class="col-sm-3 abbr" style="position: relative;padding-right: 15px;padding-left: 15px;">
212     
213    <img src="./assets/img/teaser_occnerf.png" class="teaser img-fluid z-depth-1" style="width=100;height=40%" />
214     
215    <abbr class="badge">TIP</abbr>
216    
217    
218  </div>
219  <div class="col-sm-9" style="position: relative;padding-right: 15px;padding-left: 20px;">
220      <div class="title"><a href="https://ieeexplore.ieee.org/abstract/document/11003427">OccNeRF: Advancing 3D Occupancy Prediction in Lidar-free Environments</a></div>
221      <div class="author"><strong>Chubin Zhang</strong>, Juncheng Yan, Yi Wei, Jiaxin Li, Li Liu, Yansong Tang*, Yueqi Duan, Jiwen Lu (*Corresponding authors)</div>
222      <div class="periodical"><em>IEEE Transactions on Image Processing (TIP)</em>
223      </div>
224    <div class="links">
225       
226      <a href="https://ieeexplore.ieee.org/abstract/document/11003427" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">PDF</a>
227      
228       
229      <a href="https://github.com/LinShan-Bin/OccNeRF" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">
229Code</a>
230      
231       
232      <a href="https://lin-shan.com/OccNeRF/" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">Page</a>
233      
234       
235      <a href="https://arxiv.org/abs/2312.09243" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">arXiv</a>
236      
237      
238      
239      
240    </div>
241  </div>
242</div>
243</li>
244<br />
245
246
247
248<li>
249<div class="pub-row">
250  <div class="col-sm-3 abbr" style="position: relative;padding-right: 15px;padding-left: 15px;">
251     
252    <img src="./assets/img/teaser_sray.png" class="teaser img-fluid z-depth-1" style="width=100;height=40%" />
253     
254    <abbr class="badge">CVPR</abbr>
255    
256    
257  </div>
258  <div class="col-sm-9" style="position: relative;padding-right: 15px;padding-left: 20px;">
259      <div class="title"><a href="">Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention</a></div>
260      <div class="author">Fangfu Liu, <strong>Chubin Zhang</strong>, Yu Zheng, Yueqi Duan</div>
261      <div class="periodical"><em>IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023</em>
262      </div>
263    <div class="links">
264      
265       
266      <a href="https://github.com/liuff19/Semantic-Ray" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">
266Code</a>
267      
268       
269      <a href="https://liuff19.github.io/S-Ray/" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">Page</a>
270      
271       
272      <a href="https://arxiv.org/abs/2303.13014" class="btn btn-sm z-depth-0" role="button" target="_blank" style="font-size:12px;">arXiv</a>
273      
274      
275      
276      
277    </div>
278  </div>
279</div>
280</li>
281<br />
282
283
284
285</ol>
286</div>
287
288
289
290      <br>
291
292      
293      <p><small>Powered by Jekyll and <a href="https://github.com/yaoyao-liu/minimal-light" target="_blank" rel="noopener">Minimal Light</a> theme.</small></p>
294      
295
296      </section>
297      <footer>
298        
299      </footer>
300    </div>
301    
301<script src="/assets/js/scale.fix.js"></script>
301
302    
303  
303<script type="module" src="https://static.cloudflareinsights.com/beacon.min.js/v31edd6df95cf4e85bb4c19e7a9bdbcba1788362987495" integrity="sha512-iIg7k2xntmwu6/uSb5tpc/hySgZc4eoL31yB29W6tJFo2akwjPWcEqnCEdJvGexCL0KEQwVYv5BlowfhVz26hg==" data-cf-beacon='{"version":"2024.11.0","token":"87b86f13d308412f878cbe6b1f52e046","r":1,"spa":2}' crossorigin="anonymous"></script>
303
304</body>
305</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.