fix typo

index.html

@@ -46,13 +46,15 @@ <h2>News</h2>
 <ul>
 <li><p>09/2024: Our <a href="https://arxiv.org/abs/2405.19547">negCLIPLoss</a> paper is accepted by NeurIPS 2024 as spotlight!</p>
 </li>
+<li><p>09/2024: Attending the 2024 Mathematical and Scientific Foundations of Deep Learning Annual Meeting in New York sponsored by Simons Foundation and show our <a href="https://arxiv.org/abs/2405.19547">negCLIPLoss</a> poster!</p>
+</li>
 <li><p>06/2024: Started my internship at Microsoft!</p>
 </li>
 <li><p>01/2024: One paper (<a href="https://arxiv.org/abs/2310.00535">JoMA</a>) is accepted by ICLR 2024!</p>
 </li>
-<li><p>12/2023: Attended NeurIPS 2023 at New Orleans.</p>
+<li><p>12/2023: Attended NeurIPS 2023 in New Orleans.</p>
 </li>
-<li><p>09/2023: One paper (<a href="https://arxiv.org/abs/2305.16380">Scan&amp;Snap</a>) is accepted by NeurIPS 2024!</p>
+<li><p>09/2023: One paper (<a href="https://arxiv.org/abs/2305.16380">Scan&amp;Snap</a>) is accepted by NeurIPS 2023!</p>
 </li>
 <li><p>09/2023: Become a husky in UW!</p>
 </li>
@@ -64,7 +66,7 @@ <h2>My Favourite Papers</h2>
 We studied how to efficiently select data for multimodal pretraining tasks, drawing inspiration from both empirical observations and theoretical insights.<br /></p>
 <table class="imgtable"><tr><td>
 <img src="photos/negcliploss.png" alt="alt text" width="400px" height="180px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2405.19547">CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning</a></b> <span class="preserve-space">   </span><a href="https://github.com/ypwang61/negCLIPLoss_NormSim">[Code]</a> <a href="./pdfs/Poster_negCLIPLoss_NormSim.pdf">[Poster]</a> <a href="https://twitter.com/ypwang61/status/1798396572516151612">[Twitter]</a>  <a href="https://arxiv.org/abs/2402.02055">[Previous Versions]</a> <br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2405.19547">CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning</a></b> <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2405.19547">[Arxiv]</a> <a href="https://github.com/ypwang61/negCLIPLoss_NormSim">[Code]</a> <a href="./pdfs/Poster_negCLIPLoss_NormSim.pdf">[Poster]</a> <a href="https://twitter.com/ypwang61/status/1798396572516151612">[Twitter]</a>  <a href="https://arxiv.org/abs/2402.02055">[Previous Versions]</a> <br />
 <b>Yiping Wang</b>*, Yifang Chen*, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon S. Du <br />
 <i>NeurIPS 2024  (<font color="red">Spotlight</font>)</i><br /><br />
 tl;dr: We design universal data selection methods for CLIP pretraining and achieve near SOTA results with less than 10% of preprocessing resources. It can obtain a new SOTA in <a href="https://www.datacomp.ai/dcclip/leaderboard.html">DataComp benchmark</a> when combined with other approaches.</p>
@@ -75,15 +77,15 @@ <h2>My Favourite Papers</h2>
 We attempted to analyze the training dynamics of transformers in a mathematical way.<br /></p>
 <table class="imgtable"><tr><td>
 <img src="photos/scan.png" alt="alt text" width="400px" height="130px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2305.16380">Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer</a></b> <span class="preserve-space">   </span>  <a href="./pdfs/poster_scan_snap.pdf">[Poster]</a>  <a href="https://twitter.com/tydsh/status/1663611845603885056">[Twitter]</a><br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2305.16380">Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer</a></b> <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2305.16380">[Arxiv]</a>  <a href="./pdfs/poster_scan_snap.pdf">[Poster]</a>  <a href="https://twitter.com/tydsh/status/1663611845603885056">[Twitter]</a><br />
 Yuandong Tian, <b>Yiping Wang</b>, Beidi Chen, Simon S. Du <br />
 <i>NeurIPS 2023</i><br />
 <i><font color="red"> Oral </font> presentation at High-dimensional learning dynamics workshop @ ICML 2023</i> <br /><br />
 tl;dr: We analyze the 1-layer transformer with next token prediction loss, and rigorously prove its training process and reveal how the token is combined via self-attention layer and the nature of its inductive bias.</p>
 </td></tr></table>
 <table class="imgtable"><tr><td>
 <img src="photos/joma.png" alt="alt text" width="400px" height="130px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2310.00535">JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention</a></b> <span class="preserve-space">   </span><a href="https://twitter.com/tydsh/status/1709785496056930654">[Twitter]</a><br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2310.00535">JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention</a></b> <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2310.00535">[Arxiv]</a> <a href="https://twitter.com/tydsh/status/1709785496056930654">[Twitter]</a><br />
 Yuandong Tian, <b>Yiping Wang</b>, Zhenyu Zhang, Beidi Chen, Simon S. Du <br />
 <i>ICLR 2024</i> <br /><br />
 tl;dr: We analyze the training dynamics of multilayer transformer, characterizing the role of self-attention, MLP nonlinearity, and the learning procedure of hierarchical structure, if the data follow hierarchical generative models.</p>

index.jemdoc

@@ -30,10 +30,11 @@ Previously, I studied Computer Science and Mathematics in [https://www.zju.edu.c
 
 == News
 - 09/2024: Our [https://arxiv.org/abs/2405.19547 negCLIPLoss] paper is accepted by NeurIPS 2024 as spotlight!
+- 09/2024: Attending the 2024 Mathematical and Scientific Foundations of Deep Learning Annual Meeting in New York sponsored by Simons Foundation and show our [https://arxiv.org/abs/2405.19547 negCLIPLoss] poster!
 - 06/2024: Started my internship at Microsoft!
 - 01/2024: One paper ([https://arxiv.org/abs/2310.00535 JoMA]) is accepted by ICLR 2024!
-- 12/2023: Attended NeurIPS 2023 at New Orleans.
-- 09/2023: One paper ([https://arxiv.org/abs/2305.16380 Scan&Snap]) is accepted by NeurIPS 2024!
+- 12/2023: Attended NeurIPS 2023 in New Orleans.
+- 09/2023: One paper ([https://arxiv.org/abs/2305.16380 Scan&Snap]) is accepted by NeurIPS 2023!
 - 09/2023: Become a husky in UW!
 
 
@@ -47,7 +48,7 @@ We studied how to efficiently select data for multimodal pretraining tasks, draw
 
 ~~~
 {}{img_left}{photos/negcliploss.png}{alt text}{400}{180}
-*[https://arxiv.org/abs/2405.19547 CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning]* {{<span class="preserve-space">   </span>}}[https://github.com/ypwang61/negCLIPLoss_NormSim \[Code\]] [./pdfs/Poster_negCLIPLoss_NormSim.pdf \[Poster\]] [https://twitter.com/ypwang61/status/1798396572516151612 \[Twitter\]]  [https://arxiv.org/abs/2402.02055 \[Previous Versions\]] \n
+*[https://arxiv.org/abs/2405.19547 CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning]* {{<span class="preserve-space">  </span>}}[https://arxiv.org/abs/2405.19547 \[Arxiv\]] [https://github.com/ypwang61/negCLIPLoss_NormSim \[Code\]] [./pdfs/Poster_negCLIPLoss_NormSim.pdf \[Poster\]] [https://twitter.com/ypwang61/status/1798396572516151612 \[Twitter\]]  [https://arxiv.org/abs/2402.02055 \[Previous Versions\]] \n
     *Yiping Wang*\*, Yifang Chen\*, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon S. Du \n
     /NeurIPS 2024  ({{<font color="red">Spotlight</font>}})/\n\n
     tl;dr: We design universal data selection methods for CLIP pretraining and achieve near SOTA results with less than 10% of preprocessing resources. It can obtain a new SOTA in [https://www.datacomp.ai/dcclip/leaderboard.html DataComp benchmark] when combined with other approaches.
@@ -62,7 +63,7 @@ We attempted to analyze the training dynamics of transformers in a mathematical
 
 ~~~
 {}{img_left}{photos/scan.png}{alt text}{400}{130}
-*[https://arxiv.org/abs/2305.16380 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer]* {{<span class="preserve-space">   </span>}}  [./pdfs/poster_scan_snap.pdf \[Poster\]]  [https://twitter.com/tydsh/status/1663611845603885056 \[Twitter\]]\n
+*[https://arxiv.org/abs/2305.16380 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer]* {{<span class="preserve-space">  </span>}}[https://arxiv.org/abs/2305.16380 \[Arxiv\]]  [./pdfs/poster_scan_snap.pdf \[Poster\]]  [https://twitter.com/tydsh/status/1663611845603885056 \[Twitter\]]\n
     Yuandong Tian, *Yiping Wang*, Beidi Chen, Simon S. Du \n
     /NeurIPS 2023/\n
     /{{<font color="red"> Oral </font>}} presentation at High-dimensional learning dynamics workshop @ ICML 2023/ \n\n
@@ -71,7 +72,7 @@ We attempted to analyze the training dynamics of transformers in a mathematical
 
 ~~~
 {}{img_left}{photos/joma.png}{alt text}{400}{130}
-*[https://arxiv.org/abs/2310.00535 JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention]* {{<span class="preserve-space">   </span>}}[https://twitter.com/tydsh/status/1709785496056930654 \[Twitter\]]\n
+*[https://arxiv.org/abs/2310.00535 JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention]* {{<span class="preserve-space">  </span>}}[https://arxiv.org/abs/2310.00535 \[Arxiv\]] [https://twitter.com/tydsh/status/1709785496056930654 \[Twitter\]]\n
     Yuandong Tian, *Yiping Wang*, Zhenyu Zhang, Beidi Chen, Simon S. Du \n
     /ICLR 2024/ \n\n
     tl;dr: We analyze the training dynamics of multilayer transformer, characterizing the role of self-attention, MLP nonlinearity, and the learning procedure of hierarchical structure, if the data follow hierarchical generative models.

miscellaneous.html

@@ -36,7 +36,7 @@ <h2>Teaching
</h2>
 </ul>
 <h2>Services</h2>
 <ul>
-<li><p>Paper Reviewer: NeurIPS 2023, ICLR 2024, ICML 2024, NeurIPS 2024</p>
+<li><p>Paper Reviewer: NeurIPS 2023, ICLR 2024, ICML 2024, TF2M@ICML24, DMLR@ICML24, NeurIPS 2024</p>
 </li>
 <li><p>UW CSE Ph.D. Admission Reviewer: 2024</p>
 </li>

miscellaneous.jemdoc

@@ -10,7 +10,7 @@
 - TA in [https://courses.cs.washington.edu/courses/cse543/24au/ CSE 543 Deep Learning (24Au)]
 
 == Services
-- Paper Reviewer: NeurIPS 2023, ICLR 2024, ICML 2024, NeurIPS 2024
+- Paper Reviewer: NeurIPS 2023, ICLR 2024, ICML 2024, TF2M@ICML24, DMLR@ICML24, NeurIPS 2024
 - UW CSE Ph.D. Admission Reviewer: 2024
 
 == Honors and Awards

pub.html

@@ -26,36 +26,36 @@ <h1>Selected Publications</h1>
 <p><span class="preserve-space">(* denotes equal contribution or alphabetic ordering.)</span> <br /><br /></p>
 <table class="imgtable"><tr><td>
 <img src="photos/negcliploss.png" alt="alt text" width="400px" height="180px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2405.19547">CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning</a></b> <span class="preserve-space">   </span><a href="https://github.com/ypwang61/negCLIPLoss_NormSim">[Code]</a> <a href="./pdfs/Poster_negCLIPLoss_NormSim.pdf">[Poster]</a> <a href="https://twitter.com/ypwang61/status/1798396572516151612">[Twitter]</a>  <a href="https://arxiv.org/abs/2402.02055">[Previous Versions]</a> <br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2405.19547">CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning</a></b> <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2405.19547">[Arxiv]</a> <a href="https://github.com/ypwang61/negCLIPLoss_NormSim">[Code]</a> <a href="./pdfs/Poster_negCLIPLoss_NormSim.pdf">[Poster]</a> <a href="https://twitter.com/ypwang61/status/1798396572516151612">[Twitter]</a>  <a href="https://arxiv.org/abs/2402.02055">[Previous Versions]</a> <br />
 <b>Yiping Wang</b>*, Yifang Chen*, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon S. Du <br />
 <i>NeurIPS 2024  (<font color="red">Spotlight</font>)</i><br /><br />
 tl;dr: We design universal data selection methods for CLIP pretraining and achieve near SOTA results with less than 10% of preprocessing resources. It can obtain a new SOTA in <a href="https://www.datacomp.ai/dcclip/leaderboard.html">DataComp benchmark</a> when combined with other approaches.</p>
 </td></tr></table>
 <table class="imgtable"><tr><td>
 <img src="photos/joma.png" alt="alt text" width="400px" height="150px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2310.00535">JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention</a></b> <span class="preserve-space">   </span><a href="https://twitter.com/tydsh/status/1709785496056930654">[Twitter]</a><br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2310.00535">JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention</a></b> <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2310.00535">[Arxiv]</a> <a href="https://twitter.com/tydsh/status/1709785496056930654">[Twitter]</a><br />
 Yuandong Tian, <b>Yiping Wang</b>, Zhenyu Zhang, Beidi Chen, Simon S. Du <br />
 <i>ICLR 2024</i> <br /><br />
 tl;dr: We analyze the training dynamics of multilayer transformer, characterizing the role of self-attention, MLP nonlinearity, and the learning procedure of hierarchical structure, if the data follow hierarchical generative models.<br /><br /></p>
 </td></tr></table>
 <table class="imgtable"><tr><td>
 <img src="photos/scan.png" alt="alt text" width="400px" height="140px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2305.16380">Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer</a></b> <span class="preserve-space">   </span>  <a href="./pdfs/poster_scan_snap.pdf">[Poster]</a>  <a href="https://twitter.com/tydsh/status/1663611845603885056">[Twitter]</a><br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2305.16380">Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer</a></b> <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2305.16380">[Arxiv]</a>  <a href="./pdfs/poster_scan_snap.pdf">[Poster]</a>  <a href="https://twitter.com/tydsh/status/1663611845603885056">[Twitter]</a><br />
 Yuandong Tian, <b>Yiping Wang</b>, Beidi Chen, Simon S. Du <br />
 <i>NeurIPS 2023</i><br />
 <i><font color="red"> Oral </font> presentation at High-dimensional learning dynamics workshop @ ICML 2023</i> <br /><br />
 tl;dr: We analyze the 1-layer transformer with next token prediction loss, and rigorously prove its training process and reveal how the token is combined via self-attention layer and the nature of its inductive bias.</p>
 </td></tr></table>
 <table class="imgtable"><tr><td>
 <img src="photos/L1_A_MTRL.png" alt="alt text" width="400px" height="160px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2306.02556">Improved Active Multi-Task Representation Learning via Lasso</a></b> <br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2306.02556">Improved Active Multi-Task Representation Learning via Lasso</a></b>  <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2306.02556">[Arxiv]</a>  <br />
 <b>Yiping Wang</b>, Yifang Chen, Kevin Jamieson, Simon S. Du <br />
 <i>ICML 2023</i> <br /><br />
 tl;dr: We improve the sample complexity of active multi-task representation learning by proposing a new LASSO-based strategy.</p>
 </td></tr></table>
 <table class="imgtable"><tr><td>
 <img src="photos/cmixup.png" alt="alt text" width="400px" height="140px" />&nbsp;</td>
-<td align="left"><p><b><a href="https://arxiv.org/abs/2210.05775">C-Mixup: Improving Generalization in Regression</a></b> <span class="preserve-space">  </span><a href="https://github.com/huaxiuyao/C-Mixup">[Code]</a> <br />
+<td align="left"><p><b><a href="https://arxiv.org/abs/2210.05775">C-Mixup: Improving Generalization in Regression</a></b>  <span class="preserve-space">  </span><a href="https://arxiv.org/abs/2210.05775">[Arxiv]</a> <a href="https://github.com/huaxiuyao/C-Mixup">[Code]</a> <br />
 Huaxiu Yao*, <b>Yiping Wang</b>*, Linjun Zhang, James Zou, Chelsea Finn <br />
 <i>NeurIPS 2022</i> <br /><br />
 tl;dr: We propose a simple yet effective data augmentation method to improve generalization on regression tasks.</p>