Update index.html

index.html

@@ -91,7 +91,6 @@ <h2>Robotics Researcher, CS PhD Student at NUS</h2>
         </div>
         <div class="col-lg-9 pt-4 pt-lg-0 content" data-aos="fade-left">
           <h3>Anxing Xiao (肖岸星), Robotics Researcher &amp; Engineer</h3>
-
           <p >
             I am a Ph.D. student in Computer Science at the National University of Singapore, advised by <a href='https://www.comp.nus.edu.sg/~dyhsu/'>Prof. David Hsu</a>. My research primarily focuses on developing compositional reasoning algorithms and multimodal interaction systems for intelligent robots to adaptively perform assistive tasks in dynamic and open human-centered environments . 
             <!-- My research aims to develop autonomous robots that can reason and interact effectively with unstructured environments, especially human-centred environments. -->
@@ -208,6 +207,40 @@ <h2>Publications</h2>
         <div class="row">
 
         <!--<p>&nbsp;</p>-->
+
+
+
+        <div class="col-lg-12 pt-2 pt-lg-3 content" >
+
+          <!-- <h3><a href="https://scholar.google.com/citations?user=qrgIuiEAAAAJ&hl=en" target="_blank">  Google Scholar</a> </h3>
+          <br> -->
+
+          <h3>2024</h3>
+
+          <div class="row">
+            <div class="col-lg-12 item">
+
+              <p>
+              <strong>Octopi: Object Property Reasoning with Large Tactile-Language Models </strong>
+              <br>
+              <font color="#4e4e4e" size="4px">Samson Yu, Kelvin Lin, <strong>Anxing Xiao</strong>, Jiafei Duan, and Harold Soh     </font>
+              <br>
+              <em>Accepted to Robotics: Science and Systems (RSS) 2024. </font>
+              </em>
+              <br>
+              <a href="https://arxiv.org/abs/2405.02794">arXiv</a>
+              /
+              <a href="https://octopi-tactile-lvlm.github.io/">Website</a>
+              /
+              <a href="https://github.com/clear-nus/octopi">Code</a>
+              </p>
+
+            </div>
+          </div>
+
+        </div>
+
+
         <div class="col-lg-12 pt-2 pt-lg-3 content" >
 
           <!-- <h3><a href="https://scholar.google.com/citations?user=qrgIuiEAAAAJ&hl=en" target="_blank">  Google Scholar</a> </h3>
@@ -223,7 +256,7 @@ <h3>2023</h3>
               <br>
               <font color="#4e4e4e" size="4px">Bingyi Xia, Hao Luan, Ziqi Zhao, Xuheng Gao, Peijia Xie, <strong>Anxing Xiao</strong>, Jiankun Wang, Max Q-H Meng</font>
               <br>
-              <em>Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023. </font>
+              <em>IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023. </font>
               </em>
               <br>
               <a href="https://arxiv.org/abs/2303.06624">arXiv</a>
@@ -355,13 +388,12 @@ <h3>2020</h3>
               <br>
               <font color="#4e4e4e" size="4px">Yaqi Wu*, <strong>Anxing Xiao</strong>*, Haoyao Chen, Shiwu Zhang and Yunhui Liu</font>
               <br>
-              <em>IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Boston, MA, USA, July 2020. 
+              <em>IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) 2020. 
               </em>
               <br>
               <a href="https://arxiv.org/abs/2107.00773">arXiv</a>
               /
               <a href="https://www.youtube.com/watch?v=5pzJ8U7YyGc">Video</a>
-
             </p>
 
             </div>
@@ -462,6 +494,8 @@ <h4>Robi Butler: Multimodal Remote Interaction with Household Robotic Assistants
 The integration of above components allows Robi Butler to ground remote multimodal instruction in the real-world home environment in a zero-shot manner. 
               <br>
             <a class="btn btn-outline-primary my-1 mr-1 btn-sm" href="assets/doc/robi.pdf" target="_blank">Paper</a>
+            <a class="btn btn-outline-primary my-1 mr-1 btn-sm" href="https://youtu.be/mf4WLQFGa8c" target="_blank">Video</a>
+
           </p>
 
         </div>
@@ -485,6 +519,8 @@ <h4>Octopi: Object Property Reasoning with Large Tactile-Language Models </h4>
               In this work, we investigate combining tactile perception with language, which enables embodied systems to obtain physical properties through interaction and apply common-sense reasoning. We contribute a new dataset PHYSICLEAR, which comprises both physical/property reasoning tasks and annotated tactile videos obtained using a GelSight tactile sensor. We then introduce OCTOPI, a system that leverages both tactile representation learning and large vision-language models to predict and reason about tactile inputs with minimal language fine-tuning. Our evaluations on PHYSICLEAR show that OCTOPI is able to effectively use intermediate physical property predictions to improve physical reasoning in both trained tasks and for zero-shot reasoning. 
               <br>
             <a class="btn btn-outline-primary my-1 mr-1 btn-sm" href="https://arxiv.org/pdf/2405.02794" target="_blank">Paper</a>
+            <a class="btn btn-outline-primary my-1 mr-1 btn-sm" href="https://octopi-tactile-lvlm.github.io/" target="_blank">Website</a>
+
           </p>
         </div>
       </div>