Skip to content

Commit

Permalink
update prolip / rewas / regionvlm
Browse files Browse the repository at this point in the history
  • Loading branch information
@SanghyukChun
SanghyukChun committed Oct 25, 2024
1 parent 2087a43 commit 19def36
Show file tree
Hide file tree
Showing 4 changed files with 53 additions and 21 deletions.
65 changes: 45 additions & 20 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ <h1>Sanghyuk Chun</h1>
<h3 id="news" class="mt-5">News</h3>
<div class="mb-5 on-click-all-active">
<ul class="pl15 mb-0">
<li>10/2024 : 1 paper <sup><a href="#read-watch-and-scream-sound-generation-from-text-and-video">[ReWaS]</a></sup> is accepted at NeurIPS 2024 Workshopon Video-Language Models.</li>
<li>10/2024 : I will serve as an area chair at <a href="https://aistats.org/aistats2025/">AISTATS 2025</a></li>
<li>_9/2024 : 1 paper <sup><a href="#do-counterfactually-fair-image-classifiers-satisfy-group-fairnes">[CKD]</a></sup> is accepted at NeurIPS 2024 D&amp;B track.</li>
<li>_9/2024 : Giving a talk at SKKU (topic: "Realistic challenges and limitations of AI") <a href="https://docs.google.com/presentation/d/1s_7f3Uu6CtYrucFYQLhCJyV8l3Nhz7QZebyxpi5IwLs/edit?usp=sharing">[slide]</a></li>
Expand Down Expand Up @@ -288,6 +289,13 @@ <h3 id="papers" class="mt-5">Publications</h3>
<div class="tab-content" id="nav-tabContent">
<div class="tab-pane fade show active" id="nav-selected" role="tabpanel" aria-labelledby="nav-selected-tab">
<ul class="list-group list-group-flush list-no-border">
<li class="list-group-item">
<strong>Probabilistic Language-Image Pre-Training.</strong>
<ul>
<li><strong>Sanghyuk Chun</strong>, Wonjae Kim, Song Park, Sangdoo Yun</li>
<li><strong><em>preprint.</em></strong> <a href="media/papers/chun2024prolip.pdf">paper</a> | <a href="https://github.com/naver-ai/prolip/">code</a> | <a href="media/bibtex/chun2024prolip.txt">bibtex</a></li>
</ul>
</li>
<li class="list-group-item">
<strong>Improved Probabilistic Image-Text Representations.</strong>
<ul>
Expand Down Expand Up @@ -347,7 +355,7 @@ <h3 id="papers" class="mt-5">Publications</h3>
<strong>Toward Interactive Regional Understanding in Vision-Large Language Models</strong>
<ul>
<li>Jungbeom Lee, <strong>Sanghyuk Chun<sup>&#10059;</sup></strong>, Sangdoo Yun<sup>&#10059;</sup></li>
<li><strong><em>NAACL 2024.</em></strong> <a href="media/papers/lee2024naacl_region_vlm.pdf">paper</a> | code (tba) | <a href="media/bibtex/lee2024vlm.txt">bibtex</a></li>
<li><strong><em>NAACL 2024.</em></strong> <a href="media/papers/lee2024naacl_region_vlm.pdf">paper</a> | <a href="https://github.com/jbeomlee93/RegionVLM">code</a> | <a href="media/bibtex/lee2024vlm.txt">bibtex</a></li>
</ul>
</li>

Expand Down Expand Up @@ -439,6 +447,22 @@ <h4 class="float-left mb-0" id="papers-2024">2024</h4>
<div class="clearfix"></div>
</div>
<ul class="list-group list-group-flush list-no-border">
<li class="list-group-item li-arxiv">
<strong>Probabilistic Language-Image Pre-Training.</strong>
<ul>
<li><strong>Sanghyuk Chun</strong>, Wonjae Kim, Song Park, Sangdoo Yun</li>
<li><strong><em>preprint.</em></strong> <a href="media/papers/chun2024prolip.pdf">paper</a> | <a href="https://github.com/naver-ai/prolip/">code</a> | <a href="media/bibtex/chun2024prolip.txt">bibtex</a></li>
</ul>
</li>

<li class="list-group-item li-workshop">
<strong class="anchor-strong">Read, Watch and Scream! Sound Generation from Text and Video.</strong>
<ul>
<li>Yujin Jeong, Yunji Kim, <strong>Sanghyuk Chun</strong>, Jiyoung Lee</li>
<li><strong><em>NeurIPS 2024 Workshop on Video-Language Models</em></strong> <a href="media/papers/jeong2024rewas.pdf">paper</a> | <a href="https://naver-ai.github.io/rewas/">project page</a> | <a href="media/bibtex/jeong2024rewas.txt">bibtex</a></li>
</ul>
</li>

<li class="list-group-item li-conference">
<strong class="anchor-strong">Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study.</strong>
<ul>
Expand Down Expand Up @@ -479,14 +503,6 @@ <h4 class="float-left mb-0" id="papers-2024">2024</h4>
</ul>
</li>

<li class="list-group-item li-arxiv">
<strong class="anchor-strong">Read, Watch and Scream! Sound Generation from Text and Video.</strong>
<ul>
<li>Yujin Jeong, Yunji Kim, <strong>Sanghyuk Chun</strong>, Jiyoung Lee</li>
<li><strong><em>preprint.</em></strong> <a href="media/papers/jeong2024rewas.pdf">paper</a> | <a href="https://naver-ai.github.io/rewas/">project page</a> | <a href="media/bibtex/jeong2024rewas.txt">bibtex</a></li>
</ul>
</li>

<li class="list-group-item li-arxiv">
<strong class="anchor-strong">Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval.</strong>
<ul>
Expand All @@ -499,7 +515,7 @@ <h4 class="float-left mb-0" id="papers-2024">2024</h4>
<strong class="anchor-strong">Toward Interactive Regional Understanding in Vision-Large Language Models</strong>
<ul>
<li>Jungbeom Lee, <strong>Sanghyuk Chun<sup>&#10059;</sup></strong>, Sangdoo Yun<sup>&#10059;</sup></li>
<li><strong><em>NAACL 2024.</em></strong> <a href="media/papers/lee2024naacl_region_vlm.pdf">paper</a> | code (tba) | <a href="media/bibtex/lee2024vlm.txt">bibtex</a></li>
<li><strong><em>NAACL 2024.</em></strong> <a href="media/papers/lee2024naacl_region_vlm.pdf">paper</a> | <a href="https://github.com/jbeomlee93/RegionVLM">code</a> | <a href="media/bibtex/lee2024vlm.txt">bibtex</a></li>
</ul>
</li>

Expand Down Expand Up @@ -894,6 +910,22 @@ <h4 class="card-header no-border" id="papers-journal">Journals</h4>
</div>
<div class="tab-pane fade" id="nav-vl" role="tabpanel" aria-labelledby="nav-vl-tab">
<ul class="list-group list-group-flush list-no-border">
<li class="list-group-item">
<strong>Probabilistic Language-Image Pre-Training.</strong>
<ul>
<li><strong>Sanghyuk Chun</strong>, Wonjae Kim, Song Park, Sangdoo Yun</li>
<li><strong><em>preprint.</em></strong> <a href="media/papers/chun2024prolip.pdf">paper</a> | <a href="https://github.com/naver-ai/prolip/">code</a> | <a href="media/bibtex/chun2024prolip.txt">bibtex</a></li>
</ul>
</li>

<li class="list-group-item">
<strong>Read, Watch and Scream! Sound Generation from Text and Video.</strong>
<ul>
<li>Yujin Jeong, Yunji Kim, <strong>Sanghyuk Chun</strong>, Jiyoung Lee</li>
<li><strong><em>NeurIPS 2024 Workshop on Video-Language Models</em></strong> <a href="media/papers/jeong2024rewas.pdf">paper</a> | <a href="https://naver-ai.github.io/rewas/">project page</a> | <a href="media/bibtex/jeong2024rewas.txt">bibtex</a></li>
</ul>
</li>

<li class="list-group-item">
<strong>HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts.</strong> <span class="badge bg-danger">Oral presentation</span>
<ul>
Expand All @@ -910,14 +942,6 @@ <h4 class="card-header no-border" id="papers-journal">Journals</h4>
</ul>
</li>

<li class="list-group-item">
<strong>Read, Watch and Scream! Sound Generation from Text and Video.</strong>
<ul>
<li>Yujin Jeong, Yunji Kim, <strong>Sanghyuk Chun</strong>, Jiyoung Lee</li>
<li><strong><em>preprint.</em></strong> <a href="media/papers/jeong2024rewas.pdf">paper</a> | <a href="https://naver-ai.github.io/rewas/">project page</a> | <a href="media/bibtex/jeong2024rewas.txt">bibtex</a></li>
</ul>
</li>

<li class="list-group-item">
<strong>Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval.</strong>
<ul>
Expand All @@ -938,7 +962,7 @@ <h4 class="card-header no-border" id="papers-journal">Journals</h4>
<strong>Toward Interactive Regional Understanding in Vision-Large Language Models</strong>
<ul>
<li>Jungbeom Lee, <strong>Sanghyuk Chun<sup>&#10059;</sup></strong>, Sangdoo Yun<sup>&#10059;</sup></li>
<li><strong><em>NAACL 2024.</em></strong> <a href="media/papers/lee2024naacl_region_vlm.pdf">paper</a> | code (tba) | <a href="media/bibtex/lee2024vlm.txt">bibtex</a></li>
<li><strong><em>NAACL 2024.</em></strong> <a href="media/papers/lee2024naacl_region_vlm.pdf">paper</a> | <a href="https://github.com/jbeomlee93/RegionVLM">code</a> | <a href="media/bibtex/lee2024vlm.txt">bibtex</a></li>
</ul>
</li>

Expand Down Expand Up @@ -1366,6 +1390,7 @@ <h4 class="card-header">Professional Service</h4>
<li><strong>Conference Area Chair:</strong>
<ul>
<li>ICLR 2025</li>
<li>AISTATS 2025</li>
<li>NeurIPS 2024</li>
<li>NeurIPS Dataset and Benchmark (D&amp;B) track 2023-2024</li>
</ul>
Expand Down Expand Up @@ -1478,7 +1503,7 @@ <h4 id="interns" class="card-header">Mentees / Short-term post-doctoral collabor
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://sehyunkwon.github.io/">Sehyun Kwon</a> (Seoul National University, 2024) <span class="text-danger"> -- VL representation learning</span></li>
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://bellos1203.github.io/">Jaeyoo Park</a> (Seoul National University, 2024) <span class="text-danger"> -- VL representation learning</span></li>
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://park-jungin.github.io/">Jungin Park</a> (Visiting researcher, 2024) <span class="text-danger"> -- VL representation learning</span></li>
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://eugene6923.github.io/">Yujin Jeong</a> (Korea University, 2024) <span class="text-danger"> -- AVL representation learning</span></li>
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://eugene6923.github.io/">Yujin Jeong</a> (Korea University, 2024) <a href="#read-watch-and-scream-sound-generation-from-text-and-video">[W10]</a> <span class="text-danger"> -- AVL representation learning</span></li>
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill bg-success text-success">_</span> <a href="https://scholar.google.co.kr/citations?user=D9U_ohsAAAAJ&hl=en">Heesun Bae</a> (KAIST, 2023) <span class="text-danger"> -- VL representation learning under noisy environment</span></li>
<li><span class="badge round-pill bg-danger text-danger">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://jbeomlee93.github.io/">Jungbeom Lee</a> (Visiting researcher, 2023) <a href="#toward-interactive-regional-understanding-in-vision-large-langua">[C28]</a> <span class="text-danger"> -- VL representation learning</span></li>
<li><span class="badge round-pill bg-success text-success">_</span> <span class="badge round-pill">&nbsp;&nbsp;</span> <a href="https://sites.google.com/snu.ac.kr/eunjikim">Eunji Kim</a> (Seoul National University, 2022) <span class="text-success"> -- XAI + Probabilistic Machine</span> (the internship project is published at ICML 2023 <a href="https://arxiv.org/abs/2306.01574">[paper]</a>)</li>
Expand Down
6 changes: 6 additions & 0 deletions media/bibtex/chun2024prolip.txt
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
@article{chun2024prolip,
title={Probabilistic Language-Image Pre-Training},
author={Sanghyuk Chun and Wonjae Kim and Song Park and Sangdoo Yun},
year={2024},
journal={arXiv preprint arXiv:2410.18857},
}
3 changes: 2 additions & 1 deletion media/bibtex/jeong2024rewas.txt
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
@article{jeong2024rewas,
author={Yujin Jeong and Yunji Kim and Sanghyuk Chun and Jiyoung Lee},
title={Read, Watch and Scream! Sound Generation from Text and Video},
author={Yujin Jeong and Yunji Kim and Sanghyuk Chun and Jiyoung Lee},
year={2024},
journal={arXiv preprint arXiv:2407.05551},
}
Binary file added media/papers/chun2024prolip.pdf
View file
Binary file not shown.

0 comments on commit 19def36

Please sign in to comment.