Update

_layouts/organizers.html

@@ -2,55 +2,57 @@
 layout: default
 ---
 
+<!-- Organizers -->
 <article class="post">
 
-  <header class="post-header">
-    <h1 class="post-title">{{ page.title | escape }}</h1>
-  </header>
-
-  <div class = "post-content">
-	  <table style="border-collapse: collapse; border: none;">
-	  	{% for organizer in site.organizers %}
-		    <tr style="border: none;">
-		        <td style="border: none;">
-		            <div class="col-xs-12">
-		                <p align="center">
-		                	{% if organizer.img %}
-		                    	<img class="people-pic" src="{{ organizer.img | prepend: '/assets/img/organizers/' | prepend: site.baseurl | prepend: site.url }}" target="_blank">
-		                    {% else %}
-		                    	<img class="people-pic" src="{{ 'avatar.jpg' | prepend: '/assets/img/organizers/' | prepend: site.baseurl | prepend: site.url }}" target="_blank">
-		                    {% endif %}
-		                </p>
-		            </div>
-		        </td>
-		        <td style="border: none;">
-		            <div class="people-name text-center">
-		            	<!-- organizer name (link to webpage if provided) -->
-		            	{% if organizer.webpage %}
-		            		<a href="{{ organizer.webpage }}" target="_blank">{{ organizer.name }}</a>
-		            	{% else %}
-		            		{{ organizer.name }}
-		            	{% endif %}
-		                <br>
-		                <!-- organizer affiliation (if provided) -->
-		                {% if organizer.affil_link %}
-		                	<a href="{{ organizer.affil_link }}" target="_blank">{{ organizer.affil }}</a>
-		                {% else %}
-		                	{{ organizer.affil }}
-		                {% endif %}
-		                <!-- Additional organizer affiliation (if provided) -->
-		                {% if organizer.affil2_link %}
-		                	<br>
-		                	<a href="{{ organizer.affil2_link }}" target="_blank">{{ organizer.affil2 }}</a>
-		                {% elsif organizer.affil2 %}
-		                	<br>
-		                	{{ organizer.affil2 }}
-		                {% endif %}
-		            </div>
-		        </td>
-		    </tr>
-	    {% endfor %}
-	  </table>
-  </div>
-
-</article>
+  <h5><i><pre>"If I have seen further, it is by standing on the shoulders of giants."<br>
+							- Isaac Newton, 1675</pre></i></h5>
+
+	<div class = "post-content">
+		<table style="border-collapse: collapse; border: none; ">
+		<tr style="border: none;">
+				{% for organizer in site.organizers %}
+				  <td style="border: none; vertical-align: top; padding: 10px 10px;">
+					  <div class="col-xs-12">
+						  <p align="center">
+							  {% if organizer.img_url %}
+								  <img class="people-pic" src="{{ organizer.img_url }}" target="_blank">
+							  {% elsif organizer.img %}
+								<img class="people-pic" src="{{ organizer.img | prepend: '/assets/img/organizers/' | prepend: site.baseurl | prepend: site.url }}" target="_blank">
+							  {% else %}
+								  <img class="people-pic" src="{{ 'avatar.jpg' | prepend: '/assets/img/organizers/' | prepend: site.baseurl | prepend: site.url }}" target="_blank">
+							  {% endif %}
+						  </p>
+					  </div>
+					  <div class="people-name text-center">
+						  <!-- organizer name (link to webpage if provided) -->
+						  <span class="larger-name">
+					  {% if organizer.webpage %}
+							  <a href="{{ organizer.webpage }}" target="_blank">{{ organizer.name }}</a>
+							{% else %}
+								{{ organizer.name }}
+							{% endif %}
+					</span>
+						  <br>
+						  <!-- organizer affiliation (if provided) -->
+						  {% if organizer.affil_link %}
+							  <a href="{{ organizer.affil_link }}" target="_blank">{{ organizer.affil }}</a>
+						  {% else %}
+							  {{ organizer.affil }}
+						  {% endif %}
+						  <!-- Additional organizer affiliation (if provided) -->
+						  {% if organizer.affil2_link %}
+							  <br>
+							  <a href="{{ organizer.affil2_link }}" target="_blank">{{ organizer.affil2 }}</a>
+						  {% elsif organizer.affil2 %}
+							  <br>
+							  {{ organizer.affil2 }}
+						  {% endif %}
+					  </div>
+				  </td>
+			 {% endfor %}
+		</tr>
+		</table>
+	</div>
+
+  </article>

_organizers/organizerjanedoe.md → _organizers/0_ziyiyang.md

@@ -1,20 +1,20 @@
 ---
 # Name of the organizer
-name: Organizer Jane Doe
+name: Ziyi Yang
 
 # Link to the organizer's webpage
-webpage: https://jane.doe
+webpage: http://yzylmc.com
 
 # Primary affiliation
-affil: Buzz University
+affil: 2024(Now)
 # Link to the primary affiliation
-affil_link: https://buzz.edu
+# affil_link: https://buzz.edu
 
 # An image of the organizer (square aspect ratio works the best) (place in the `assets/img/organizers` directory)
-img: jane.jpg
+img: ziyiyang.jpeg
 
-# Secondary affiliation
-affil2: BuzzFizz Corp
-# Link to the secondary affiliation
-affil2_link: https://buzzfizz.corp
+# # Secondary affiliation
+# affil2: BuzzFizz Corp
+# # Link to the secondary affiliation
+# affil2_link: https://buzzfizz.corp
 ---

_organizers/1_benjaminspiegel.md

@@ -0,0 +1,20 @@
+---
+# Name of the organizer
+name: Benjamin A. Spiegel
+
+# Link to the organizer's webpage
+webpage: https://benjaminaspiegel.com/
+
+# Primary affiliation
+affil: 2023
+# Link to the primary affiliation
+# affil_link: https://buzz.edu
+
+# An image of the organizer (square aspect ratio works the best) (place in the `assets/img/organizers` directory)
+img: benjaminspiegel.png
+
+# # Secondary affiliation
+# affil2: BuzzFizz Corp
+# # Link to the secondary affiliation
+# affil2_link: https://buzzfizz.corp
+---

_organizers/2_sakettiwari.md

@@ -0,0 +1,20 @@
+---
+# Name of the organizer
+name: Saket Tiwari
+
+# Link to the organizer's webpage
+webpage: https://saketirl.github.io/
+
+# Primary affiliation
+affil: 2022
+# Link to the primary affiliation
+# affil_link: https://buzz.edu
+
+# An image of the organizer (square aspect ratio works the best) (place in the `assets/img/organizers` directory)
+img: sakettiwari.jpeg
+
+# # Secondary affiliation
+# affil2: BuzzFizz Corp
+# # Link to the secondary affiliation
+# affil2_link: https://buzzfizz.corp
+---

_organizers/3_kaiyuzheng.md

@@ -0,0 +1,20 @@
+---
+# Name of the organizer
+name: Kaiyu Zheng
+
+# Link to the organizer's webpage
+webpage: https://kaiyuzheng.me/
+
+# Primary affiliation
+affil: 2021
+# Link to the primary affiliation
+# affil_link: https://buzz.edu
+
+# An image of the organizer (square aspect ratio works the best) (place in the `assets/img/organizers` directory)
+img: kaiyuzheng.png
+
+# # Secondary affiliation
+# affil2: BuzzFizz Corp
+# # Link to the secondary affiliation
+# affil2_link: https://buzzfizz.corp
+---

_organizers/4_samlobel.md

@@ -0,0 +1,20 @@
+---
+# Name of the organizer
+name: Sam Lobel
+
+# Link to the organizer's webpage
+webpage: https://samlobel.github.io/
+
+# Primary affiliation
+affil: 2020
+# Link to the primary affiliation
+# affil_link: https://buzz.edu
+
+# An image of the organizer (square aspect ratio works the best) (place in the `assets/img/organizers` directory)
+img: samlobel.jpeg
+
+# # Secondary affiliation
+# affil2: BuzzFizz Corp
+# # Link to the secondary affiliation
+# affil2_link: https://buzzfizz.corp
+---

_organizers/5_lucaslehnert.md

@@ -0,0 +1,20 @@
+---
+# Name of the organizer
+name: Lucas Lehnert
+
+# Link to the organizer's webpage
+webpage: https://lucaslehnert.github.io/
+
+# Primary affiliation
+affil: 2019
+# Link to the primary affiliation
+# affil_link: https://buzz.edu
+
+# An image of the organizer (square aspect ratio works the best) (place in the `assets/img/organizers` directory)
+img: lucaslehnert.jpeg
+
+# # Secondary affiliation
+# affil2: BuzzFizz Corp
+# # Link to the secondary affiliation
+# affil2_link: https://buzzfizz.corp
+---

_speakers/1_stefanoalbrecht.md

@@ -1,6 +1,6 @@
 ---
 # Name of the speaker
-name: Stefano Albrecht
+name: Stefano V. Albrecht
 
 # Link to the speaker's webpage
 webpage: https://agents.inf.ed.ac.uk/stefano-albrecht/

contactus.md

@@ -4,4 +4,4 @@ title: Contact Us
 permalink: /contactus/
 ---
 
-Here's how you can contact us ...
+Please feel free to email [us](mailto:[email protected]) if you have any question or suggestion!

index.md

@@ -23,12 +23,12 @@ Brown Robotics Talks consists of BigAI talks and lab talks (CIT 115). From sprin
 <tbody>
   <tr>
     <td>02/02</td>
-    <td>Deep Reinforcement Learning for Multi-Agent Interaction</td>
-    <td>Stefano Albrecht</td>
+    <td><b>Deep Reinforcement Learning for Multi-Agent Interaction</b></td>
+    <td>Stefano V. Albrecht</td>
   </tr>
   <tr>
     <td>03/01</td>
-    <td>TBD</td>
+    <td><b>TBD</b></td>
     <td>Felix Yanwei Wang</td>
   </tr>
 </tbody>

pasttalks.md

@@ -4,8 +4,8 @@ title: Past Talks
 permalink: /pasttalks/
 ---
 
-You'll need a Brown account to access the recordings.
-
+(You'll need a Brown account to access the recordings.)
+<h2>2023</h2>
 <table>
 <thead>
   <tr>
@@ -15,8 +15,80 @@ You'll need a Brown account to access the recordings.
 </thead>
 <tbody>
   <tr>
-    <td>Regularization in Neural Networks: A Probabilistic Perspective [<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=0e1cdf54-2b41-42cf-bb3f-b0cb01325be8' target="_blank">recording</a>]</td>
-    <td><a href='https://timrudner.com/' target="_blank">Tim Rudner</a></td>
+    <td><b>Regularization in Neural Networks: A Probabilistic Perspective</b> [<a href='abstracts/timrudner.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=0e1cdf54-2b41-42cf-bb3f-b0cb01325be8' target="_blank">recording</a>]</td>
+    <td><a href='https://timrudner.com/' target="_blank">Tim Rudner</a> [<a href='bios/timrudner.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Broadening Robot Dexterity: Leveraging Elements in Manipulation Task Environments</b> [<a href='abstracts/xianyicheng.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=f414da95-cf41-4468-97b9-b0bd013952ad' target="_blank">recording</a>]</td>
+    <td><a href='https://xianyicheng.github.io/' target="_blank">Xianyi Cheng</a> [<a href='bios/xianyicheng.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>The Hessian Perspective into the Nature of Neural Networks</b> [<a href='abstracts/sidakpalsingh.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=40316280-6ebd-4e0b-ba2a-b0b6013255a1' target="_blank">recording</a>]</td>
+    <td><a href='http://sidakpal.com/' target="_blank">Sidak Pal Singh</a> [<a href='bios/sidakpalsingh.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Quasimetric Reinforcement Learning</b> [<a href='abstracts/tongzhouwang.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=9c19b86c-ef96-44f7-bcaf-b0af0120a03f' target="_blank">recording</a>]</td>
+    <td><a href='https://www.tongzhouwang.info/' target="_blank">Tongzhou Wang</a> [<a href='bios/tongzhouwang.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Generalizing Beyond Your Data through Compositional Energy Functions</b> [<a href='abstracts/yilundu.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=ebb11f5d-8bd9-4ca0-93a5-b0a8011c6ff7' target="_blank">recording</a>]</td>
+    <td><a href='https://yilundu.github.io/' target="_blank">Yilun Du</a> [<a href='bios/yilundu.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>A2Perf: Benchmarking Autonomous Agents for the Real World</b> [<a href='abstracts/ikeuchendu.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=0fcab887-5eda-4de9-ac5d-b0a1011838e0' target="_blank">recording</a>]</td>
+    <td><a href='https://ikeuchendu.com/' target="_blank">Ike Uchendu</a> [<a href='bios/ikeuchendu.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Towards Social Autotelic Agents: Open-Ended Skill Learning with Goals, Language and Intrinsically Motivated Reinforcement Learning</b> [<a href='abstracts/cedriccolas.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=fa70f372-bfae-4b0c-b197-b09a011e2547' target="_blank">recording</a>]</td>
+    <td><a href='https://ccolas.github.io/' target="_blank">Cédric Colas</a> [<a href='bios/cedriccolas.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Natural Language Task Specification for Robots</b> [<a href='abstracts/jasonliu.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=e9a7bf68-21e3-48a2-9a09-b0930119601e' target="_blank">recording</a>]</td>
+    <td><a href='https://jasonxyliu.github.io/' target="_blank">Jason Liu</a> [<a href='bios/jasonliu.txt' target="_blank">bio</a>]</td>
+  </tr>
+ <tr>
+    <td><b>Deep Symbol Generation and Rule Learning</b> [<a href='abstracts/alperahmetoglu.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=eebf9755-4855-4d5e-8e0d-b08c011f6596' target="_blank">recording</a>]</td>
+    <td><a href='https://alpera.xyz/' target="_blank">Alper Ahmetoglu</a> [<a href='bios/alperahmetoglu.txt' target="_blank">bio</a>]</td>
+  </tr> 
+  <tr>
+    <td><b>Pragmatic, Uncertainty Guided Reinforcement Learning</b> [<a href='abstracts/taylorkillian.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=1393288a-7bbe-4dc8-beb9-b085011f7d87' target="_blank">recording</a>]</td>
+    <td><a href='https://twkillian.github.io/' target="_blank">Taylor Killian</a> [<a href='bios/taylorkillian.txt' target="_blank">bio</a>]</td>
+  </tr> 
+  <tr>
+    <td><b>Grounded Understanding of Actions and Language via Bayesian Inverse Planning</b> [<a href='abstracts/tanzhixuan.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=4e8ad957-0aaf-45f5-8189-b03f01293192' target="_blank">recording</a>]</td>
+    <td><a href='https://ztangent.github.io/' target="_blank">Tan Zhi-Xuan</a></td>
+  </tr> 
+  <tr>
+    <td><b>Improving Unsupervised Visual Program Inference with Code Rewriting Families</b> [<a href='abstracts/adityaganeshan.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=6085a516-a1a9-4d00-9f12-aff90117cf62' target="_blank">recording</a>]</td>
+    <td><a href='https://bardofcodes.github.io/' target="_blank">Aditya Ganeshan</a> [<a href='bios/adityaganeshan.txt' target="_blank">bio</a>]</td>
+  </tr> 
+  <tr>
+    <td><b>Inventing Plannable Abstractions from Demonstrations</b> [<a href='abstracts/nishanthkumar.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=7dfa10b7-d608-49f4-852e-aff201226421' target="_blank">recording</a>]</td>
+    <td><a href='https://nishanthjkumar.com/' target="_blank">Nishanth Kumar</a> [<a href='bios/nishanthkumar.txt' target="_blank">bio</a>]</td>
+  </tr> 
+  <tr>
+    <td><b>Equivariant Learning for Robotic Manipulation</b> [<a href='abstracts/dianwang.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=da9756a6-0ac9-46e0-94bc-afeb01205379' target="_blank">recording</a>]</td>
+    <td><a href='https://pointw.github.io/' target="_blank">Dian Wang</a> [<a href='bios/dianwang.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Scaling Goal-based Exploration via Pruning Proto-goals</b> [<a href='abstracts/akhilbagaria.txt' target="_blank">abstract</a>] & <b>Learning with Program Induction</b> [<a href='abstracts/skyethompson.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=45a45033-c460-483b-a447-afdd0120a6f7' target="_blank">recording</a>]</td>
+    <td><a href='https://abagaria.github.io/' target="_blank">Akhil Bagaria</a> & <a href='https://scholar.google.com/citations?user=KdcjezcAAAAJ&hl=en' target="_blank">Skye Thompson</a></td>
+  </tr>
+  <tr>
+    <td><b>Open and Efficient Reinforcement Learning from Human Feedback</b> [<a href='abstracts/louiscastricato.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=3feed4f2-dd74-4c98-8a45-afba0130743c' target="_blank">recording</a>]</td>
+    <td><a href='https://www.louiscastricato.com/' target="_blank">Louis Catricato</a> [<a href='bios/louiscastricato.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>The Uninteded Consequences of Discount Regularization</b> [<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=4b958ce6-284f-408e-8114-afb3012de8aa' target="_blank">recording</a>]</td>
+    <td><a href='https://sarahrathnam.github.io/' target="_blank">Sarah Rathnam</a> [<a href='bios/sarahrathnam.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Interpretable Artificial Intelligence for Personalized Human-Robot Collaboration</b> [<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=30668346-9259-4a4c-a469-afac0132df7e' target="_blank">recording</a>]</td>
+    <td><a href='https://www.rohanpaleja.com/' target="_blank">Rohan Paleja</a> [<a href='bios/rohanpaleja.txt' target="_blank">bio</a>]</td>
+  </tr>
+  <tr>
+    <td><b>Choreorobotics: An Emerging Discipline</b> [<a href='abstracts/catiecuan.txt' target="_blank">abstract</a>][<a href='https://brown.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=4d49fce5-d94f-4935-b98c-afa5012de675' target="_blank">recording</a>]</td>
+    <td><a href='https://catiecuan.com/' target="_blank">Catie Cuan</a> [<a href='bios/catiecuan.txt' target="_blank">bio</a>]</td>
   </tr>
 </tbody>
 </table>

pasttalks/abstracts/adityaganeshan.txt

@@ -0,0 +1 @@
+3D Data is often modeled with discrete symbolic structure to improve editability and interpretability. However, inferring this symbolic representation directly from the data is challenging - learning methods often suffer due to poor gradient estimation over stochastic computational graphs (especially with categorical distributions). An alternate strategy is to bootstrap a neurally guided search process by increasing the likelihood of “good” structures discovered during the search itself. In this talk, I will first present this approach, which we term “bootstrapped learning” and then present my recent work, which improves neurally guided inference of visual programs by code rewriting. Our work improves neurally guided visual program inference across different visual languages and matches the reconstruction accuracy of domain specific architectures while inferring concise and interpretable programs. Overall, the talk with present the challenges associated with inferring symbolic representations from 3D data, and how bootstrapped learning and code rewriting can aid with this task.

pasttalks/abstracts/akhilbagaria.txt

@@ -0,0 +1 @@
+One of the gnarliest challenges in reinforcement learning is exploration that scales to vast domains, where novelty-, or coverage-seeking behavior falls short. Goal-directed, purposeful behaviors are able to overcome this, but rely on a good goal space. The core challenge in goal discovery is finding the right balance between generality (not hand-crafted) and tractability (useful, not too many). Our approach explicitly seeks the middle ground, enabling the human designer to specify a vast but meaningful proto-goal space, and an autonomous discovery process to narrow this to a narrow space of controllable, reachable, novel, and relevant goals. The effectiveness of goal-conditioned exploration with the latter is then demonstrated in three challenging environments.