Hosted as part of the Machine Learning and AI Seminar Series in partnership with the DSI Foundations of Data Science Center and the Department of Statistics, Arts and SciencesColumbia Engineering


Speaker

Tom Goldstein headshot

Tom Goldstein, Volpi-Cupal Endowed Professor of Computer Science, Director of the Maryland Center for Machine Learning, University of Maryland


Event Details

Friday, February 20, 2026 (11:00 AM – 12:00 PM ET)

Location: School of Social Work, Room C03

REGISTRATION DEADLINE: The Columbia Morningside campus is open to the Columbia community. If you do not have an active CUID, the deadline to register is at 12:00 PM the day before the event.

Register


Talk Information

Alternative Test-Time Compute Scaling Strategies for Generative Models

Abstract: Recent trends in LLM development have focused on “Reasoning” models that expend large amounts of compute to improve their performance at inference time by producing many tokens. In this talk, we consider alternatives to the many-token paradigm.  We will focus on models that perform efficient latent reasoning without verbalizing their outputs as tokens. We will also consider new generation strategies that bypass arduous and expensive token generating processes altogether.