Winter Robotics Colloquium: Marynel Vázquez (Yale University) @uwcse

Uploaded March 2026 | Updated September 2026, 2 weeks ago

Title: Beyond Physical Intelligence: Why Generalist Robots Require Social Intelligence
Speaker: Marynel Vázquez (Yale University)
Date: Friday, February 27 2026

Abstract: As the robotics industry moves toward deploying generalist agents in unstructured human environments, such as homes and workplaces, the research focus has largely remained on physical intelligence. While mastering physical tasks is essential, social intelligence is a critical missing piece for widespread technology adoption. To be truly effective, robots must understand, navigate, and manage the nuances of interpersonal interaction. In this talk, I will discuss two aspects of social intelligence that are fundamental for Human-Robot Interaction (HRI). The first one pertains understanding social phenomena that emerges in group interactions and that robots can potentially leverage to navigate complex social situations. The second one is implicit human feedback, i.e., communicative signals that are given off “for free” by humans and that require interpretation. Robots can leverage such implicit feedback to predict how people perceive them and better collaborate with users. Finally, I will reflect on how the latest advancements in machine learning are fundamentally reshaping the way we approach research in Human-Robot Interaction.

Bio: Marynel Vázquez is an Assistant Professor in Yale’s Computer Science Department, where she leads the Interactive Machines Group. Her research investigates fundamental problems in Human-Robot Interaction and Artificial Social Intelligence, often motivated by challenges or opportunities that arise in group human-robot interactions. Marynel received her bachelor's degree in Computer Engineering from Universidad Simón Bolívar in 2008, and obtained her M.S. and Ph.D. in Robotics from Carnegie Mellon University in 2013 and 2017, respectively. Before joining Yale, she was a collaborator of Disney Research and a Post-Doctoral Scholar at the Stanford Vision & Learning Lab. Marynel received a 2024 AFOSR YIP Award, a 2022 NSF CAREER Award, two Amazon Research Awards, and a Google Research Scholar award. Her work has been recognized with a 2025 IJCAI Early Career Spotlight, best paper awards at ACM/IEEE HRI 2023 and IEEE RO-MAN 2022 as well as nominations for paper awards at ACM/IEEE HRI 2021, IEEE IROS 2018, and IEEE RO-MAN 2016.

This video is closed captioned.

Winter Robotics Colloquium: Marynel Vázquez (Yale University)

Taskar Center Events: Tools for Equitable Transportation Planning with the TDEI Infrastructure

[Audio Descriptions] I Am CSE: Kyle Johnson

2024 Fall Robotics Colloquium: Kiana Ehsani (PRIOR and the Allen Institute for AI)

Allen School Colloquium: Productively Programming Accelerated Computing Systems

2025 Winter Robotics Colloquium: Katsu Ikeuchi (Principal Researcher at Microsoft)

Parables on the Power of Planning in AI: From Poker to Diplomacy: Noam Brown (OpenAI)

FlowRing: Integrated Microgesture and Surface Interaction Ring for Versatile XR Input

Learning, Reasoning, and Planning with Neuro-Symbolic Concepts–Jiayuan Mao (MIT)

$Pareto-efficient AI systems—Simran Arora (Stanford) Allen School Colloquia Series Title: Pareto-efficient AI systems: Expanding the quality and efficiency frontier of AI Speaker: Simran Arora (Stanford) Date: April 1, 2025 Abstract: We have made exciting progress in AI by scaling massive models on massive amounts of data center compute. However, this represents a small fraction of AI’s potential. My work expands the Pareto frontier between the AI capabilities we can achieve and the long tail of compute constraints. In this talk, we piece-by-piece build up to a language model architecture that expands the Pareto frontier between quality and throughput efficiency. The Transformer, AI’s current workhorse architecture, is memory hungry, limiting its throughput, or amount of data it can process per second. This has led to a Cambrian explosion of alternate architecture candidates proposed across prior work. Prior work paints an exciting picture: there are architectures that are asymptotically faster than the Transformer, while also matching its quality. However, I ask, if we’re using asymptotically faster building blocks, what if anything are we giving up in quality? 1. In part one, we understand the tradeoffs and show indeed, there’s no free lunch. I present my work to identify and explain the fundamental quality and efficiency tradeoffs between different classes of architectures. Methods I developed for this analysis are now ubiquitous in the development of efficient language models. 2. In part two, we measure how existing architecture candidates fare along on the tradeoff space. While many proposed architectures are asymptotically fast, they are not wall-clock fast compared to the Transformer. I present ThunderKittens, a programming library that I built to help AI researchers develop hardware-efficient AI algorithms. 3. In part three, we expand the Pareto frontier of the tradeoff space. I present the BASED architecture, which is built from simple, hardware-efficient components. In culmination, I released a suite of state-of-the-art 8B-405B parameter Transformer-free language models, per standard evaluations, all on an academic budget. Given the massive investment into AI models, this work blending AI and systems has had significant impact and adoption in research, open-source, and industry. Bio: Simran Arora is a PhD student at Stanford University advised by Chris Ré. Her research blends AI and systems towards expanding the Pareto frontier between AI capabilities and efficiency. Her machine learning research has appeared as Oral and Spotlight presentations at NeurIPS, ICML, and ICLR, including an Outstanding Paper award at NeurIPS and Best Paper award at ICML ES-FoMo. Her systems work has appeared at VLDB, SIGMOD, CIDR, and CHI, and her systems artifacts are widely used in research, open-source, and industry. In 2023, Simran created and taught the CS229s Systems for Machine Learning course at Stanford. She has also been supported by a SGF Sequoia Fellowship and the Stanford Computer Science Graduate Fellowship. This video is closed captioned.$

IFDS Workshop–Multi-frequency progressive refinement for learned inverse scattering