Machine Learning and Friends Lunch

Machine Learning and Friends Lunch featuring Michael Boratko, a research scientist at Google DeepMind.

David Burt is a postdoc in Professor Tamara Broderick’s group at the MIT Laboratory For Information and Decision Systems.

David Held is an Associate Professor at Carnegie Mellon University in the Robotics Institute and is the director of the RPAD lab: Robots Perceiving And Doing.

Karin de Langis, PhD candidate at University of Minnesota, studies artificial cognition in LLMs, explaining failures and comparing cognitive control vs humans.

Analyze Transformer attention via QK space, decomposing it into low-rank, interpretable features that explain why tokens attend and how attention scores arise.

Robot dexterity needs more than scale: I’ll show how structured affordance, contact, and motion reasoning links foundation models to open-world control.

Machine Learning and Friends Lunch featuring Sherry Yang, Assistant Professor of Computer Science at NYU Courant and a scientist at Google DeepMind.

Ryan Louie is a postdoctoral researcher in the Computer Science Department at Stanford University.

Machine Learning and Friends Lunch featuring Sherry Wu, assistant professor at the Human-Computer Interaction Institute at Carnegie Mellon University.

This talk explains how self-play can train autonomous driving systems in simulation, achieving realistic and robust performance without human data.

LLMs aid science but struggle to generalize. This talk explores capturing expert intuition and building agents for complex scientific reasoning.

Machine Learning and Friends Lunch featuring Wei-Chiu Ma, an Assistant Professor of Computer Science at Cornell University.