Full Professor, University of Texas, Austin
3 papers at NeurIPS 2025
This paper proposes VIBE, an annotation-free method that selects video summaries for human decision-making by scoring task relevance and visual grounding without retraining.
We characterize and provide algorithms for multi-environment POMDPs.
We propose a cooperative bargaining algorithm where a mediator has access to only the preferred direction oracle of each agent (and not utilities).