<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><i>Department of Computer Science Presents</i><div><i><br></i></div><div><b>Siddharth Karamcheti</b></div><div><b>PhD Candidate</b></div><div><b>Stanford University</b></div><div><b><br></b></div><div><b>Wednesday, April 9th</b></div><div><b>3:30pm - 4:30pm </b></div><div><b>In-Person: John Crerar Library Rm 390</b></div><div><b><br></b></div><div><b>Title: Language-Drive Learning for Interactive Robotics</b></div><div><b><br></b></div><div><b>Abstract: </b><span style="white-space: pre-wrap; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline;">Building and deploying broadly capable robots requires systems that can efficiently learn from and work with people. To achieve this, robots must balance </span><span style="white-space: pre-wrap; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline;">capability</span><span style="white-space: pre-wrap; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline;"> — the fundamental tools necessary to enable real-world deployment — and </span><span style="white-space: pre-wrap; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline;">sustainability</span><span style="white-space: pre-wrap; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline;"> — the ability to grow and adapt through human feedback. In this talk, I will motivate language-driven learning to tackle these axes, providing robots with better abstractions for perception, action, and human-robot interaction. Towards capability, I will present Voltron, our approach for using language to learn visual representations that can be efficiently adapted for diverse robotics tasks. Building on these ideas, I will discuss Prismatic, our experimental framework for developing visually-conditioned language models and vision-language-action policies at scale. Towards sustainability, I will next introduce Vocal Sandbox, a new framework that integrates these models to develop collaborative robots that can work alongside human partners, using language to express uncertainty and learn new behaviors from real-time interactions. Finally, I will conclude with open challenges for enhancing both the capability and sustainability of modern robots, with directions for future work.</span></div><div><b><br></b></div><div><b>Bio: </b>Si<span style="white-space: pre-wrap;">ddharth Karamcheti is a final year PhD student at Stanford University advised by Dorsa Sadigh and Percy Liang, and a robotics intern at the Toyota Research Institute. His research focuses on robot learning, natural language processing, and human-robot interaction, with a goal of developing scalable approaches for human-robot collaboration. Prior to the PhD, he earned his bachelor’s degree in Computer Science and Literary Arts at Brown University, where he worked with Eugene Charniak and Stefanie Tellex. He is a recipient of the Open Philanthropy AI Fellowship (2018), is an RSS Pioneer (2024), and his research has won paper awards at conferences such as RSS, CoRL, ICRA, and ACL.</span></div><div><span style="white-space: pre-wrap;"><br></span></div><div><span style="white-space-collapse: preserve;"><img alt="skaramcheti.jpeg" src="cid:DF757B7B-2E3A-4961-8618-3FA11519C874"></span></div><div><span style="white-space-collapse: preserve;"><br></span></div><div><span style="white-space-collapse: preserve;"><b>Host: Sarah Sebo </b></span></div><div><span style="white-space-collapse: preserve;"><b><br></b></span></div><div><span style="white-space-collapse: preserve;"><b>---</b></span></div><div><div>
<meta charset="UTF-8"><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div>Holly Santos<br>Executive Assistant to Hank Hoffmann, Liew Family Chair<br>Department of Computer Science<br>The University of Chicago<br>5730 S Ellis Ave-217 Chicago, IL 60637<br>P: 773-834-8977<br>hsantos@uchicago.edu</div><div><br></div></div><br class="Apple-interchange-newline"></div><br class="Apple-interchange-newline"></div><br class="Apple-interchange-newline"><br class="Apple-interchange-newline">
</div>
<br></div></body></html>