Skip to content

Commit

Permalink
Update index.html
Browse files Browse the repository at this point in the history
  • Loading branch information
@ewanlee
ewanlee authored May 6, 2024
1 parent 769e3de commit 5017675
Showing 1 changed file with 21 additions and 71 deletions.
92 changes: 21 additions & 71 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@ <h2 class="title is-3">About this tutorial</h2>
<div class="column is-full-width">
<h2 class="title is-3">Schedule</h2>
<p>
Our tutorial will be held on July 9 (all the times are based on EDT = Toronto local time).
Our tutorial will be held on May 7 (all the times are based on NZST = New Zealand local time).
<em>Slides may be subject to updates.</em>
</p>

Expand All @@ -174,57 +174,32 @@ <h2 class="title is-3">Schedule</h2>
</thead>
<tbody>
<tr>
<td class="tg-0lax">14:00—14:15</td>
<td class="tg-0lax">Section 1: Introduction <a href="./slides/1-intro.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Danqi</td>
<td class="tg-0lax">14:00—14:55</td>
<td class="tg-0lax">Section 1: Introduction, Definition & Preliminaries <a href="./slides/1-intro.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Xiangfeng</td>
</tr>
<tr>
<td class="tg-0lax">14:15—14:25</td>
<td class="tg-0lax">Section 2: Definition & Preliminaries <a href="./slides/2-definition.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Sewon</td>
<td class="tg-0lax">14:55—15:55</td>
<td class="tg-0lax">Section 2: Reinforcement Learning for VM Scheduling <a href="./slides/2-rl4vm.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Junjie</td>
</tr>
<tr>
<td class="tg-0lax">14:25—15:00</td>
<td class="tg-0lax">Section 3: Retrieval-based LMs: Architecture <a href="./slides/3-architecture.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Sewon</td>
</tr>
<tr>
<td class="tg-0lax">15:00—15:25</td>
<td class="tg-0lax">Section 4: Retrieval-based LMs: Training <a href="./slides/4-training.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Zexuan</td>
</tr>
<tr>
<td class="tg-0lax">15:25—15:30</td>
<td class="tg-0lax">15:55—16:00</td>
<td class="tg-0lax">Q & A Session I</td>
<td class="tg-0lax"></td>
</tr>
<tr>
<td class="tg-0lax">15:30—16:00</td>
<td class="tg-0lax">16:00—16:30</td>
<td class="tg-0lax">Coffee break</td>
<td class="tg-0lax"></td>
</tr>
<tr>
<td class="tg-0lax">16:00—16:25</td>
<td class="tg-0lax">Section 4 (Cont’d): Retrieval-based LMs: Training <a href="./slides/4-training.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Zexuan</td>
</tr>
<tr>
<td class="tg-0lax">16:25—17:00</td>
<td class="tg-0lax">Section 5: Retrieval-based LMs: Applications <a href="./slides/5-application.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Akari</td>
<td class="tg-0lax">16:30—17:30</td>
<td class="tg-0lax">Section 3: Reinforcement Learning for Multi-Agent Pathfinding <a href="./slides/3-rl4mapf.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Wenhao</td>
</tr>
<tr>
<td class="tg-0lax">17:00—17:10</td>
<td class="tg-0lax">Section 6: Extension: Multilingual & Multimodal <a href="./slides/6-extension.pdf" target='_blank'>[Slides]</a></td>
<td class="tg-0lax">Akari</td>
</tr>
<tr>
<td class="tg-0lax">17:10—17:20</td>
<td class="tg-0lax">Section 7: Challenges & Opportunities <a href="./slides/7-conclusion.pdf" target='_blank'>[Slides]</a> <a href="./slides/references.pdf" target='_blank'>[References]</a></td>
<td class="tg-0lax">Danqi</td>
</tr>
<tr>
<td class="tg-0lax">17:20—17:30</td>
<td class="tg-0lax">17:30—17:40</td>
<td class="tg-0lax">Q & A Session II</td>
<td class="tg-0lax"></td>
</tr>
Expand All @@ -239,12 +214,9 @@ <h2 class="title is-3">Schedule</h2>
<div class="column is-full-width">
<h2 class="title is-3">Reading List</h2>

<p><b>Bold papers</b> are discussed in detail during our tutorial.</p>

<br />


<h3 class="title is-5">Section 3: Architecture</h3>
<h3 class="title is-5">Section 1: Introduction</h3>

<ul>
<li><a href="https://arxiv.org/abs/2002.08909"><b>REALM: Retrieval-Augmented Language Model Pre-Training</b></a> (Guu et al., 2020)</li>
Expand All @@ -265,7 +237,7 @@ <h3 class="title is-5">Section 3: Architecture</h3>

<br />

<h3 class="title is-5">Section 4: Training</h3>
<h3 class="title is-5">Section 2: VM Scheduling</h3>

<ul>
<li><a href="https://arxiv.org/abs/2004.04906"><b>Dense Passage Retrieval for Open-Domain Question Answering</b></a> (Karpukhin et al., 2020)</li>
Expand All @@ -282,7 +254,7 @@ <h3 class="title is-5">Section 4: Training</h3>

<br />

<h3 class="title is-5">Section 5: Application</h3>
<h3 class="title is-5">Section 3: Multi-Agent Pathfinding</h3>

<ul>
<li><a href="https://arxiv.org/abs/2208.03299"><b>Atlas: Few-shot Learning with Retrieval Augmented Language Models</b></a> (Izacard et al., 2022; also in Section 4)</li>
Expand All @@ -303,28 +275,6 @@ <h3 class="title is-5">Section 5: Application</h3>
<li><a href="https://arxiv.org/abs/2305.14251">FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation</a> (Min et al., 2023)</li>
<!-- <li><a href="https://arxiv.org/abs/2305.14888">Privacy Implications of Retrieval-Based Language Models</a></li> -->
</ul>

<br />

<h3 class="title is-5">Section 6: Extension</h3>

<ul>
<li><a href="https://arxiv.org/abs/2107.11976">One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval</a> (Asai et al., 2021)</li>
<li><a href="https://arxiv.org/abs/2211.12561">Retrieval-Augmented Multimodal Language Modeling</a> (Yasunaga et al., 2023)</li>
</ul>
<!--<ul>
<li><a href="https://arxiv.org/abs/2107.11976">One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval</a></li>
<li><a href="https://arxiv.org/abs/2211.12561">Retrieval-Augmented Multimodal Language Modeling</a></li>
</ul> -->


<br />
<h3 class="title is-5">Section 7: Challenges & Opportunities</h3>
<ul>
<li><a href="https://arxiv.org/abs/2305.14625">KNN-LM Does Not Improve Open-ended Text Generation</a> (Wang et al., 2023)</li>
<li><a href="https://arxiv.org/abs/2212.09146">Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model</a> (BehnamGhader et al., 2022)</li>
<li><a href="https://arxiv.org/abs/2212.14024">Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP</a> (Khattab et al., 2022)</li>
</ul>
</div>
</div>
</section>
Expand All @@ -333,11 +283,11 @@ <h3 class="title is-5">Section 7: Challenges & Opportunities</h3>
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@article{ retrieval-lm-tutorial,
author = { Asai, Akari and Min, Sewon and Zhong, Zexuan and Chen, Danqi },
title = { ACL 2023 Tutorial: Retrieval-based Language Models and Applications },
journal = { ACL 2023 },
year = { 2023 },
<pre><code>@article{ rl4or-tutorial,
author = { Sheng, Junjie and Hua, Yun and Li, Wenhao and Wang, Xiangfeng },
title = { AAMAS 2024 Tutorial: Reinforcement Learning for Operations Research: Unlocking New Possibilities },
journal = { AAMAS 2024 },
year = { 2024 },
}</code></pre>
</div>
</section>
Expand Down

0 comments on commit 5017675

Please sign in to comment.