Ryo Hachiuma

Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models

Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in

Unified Reinforcement and Imitation Learning for Vision-Language Models

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

Towards Predicting Any Human Trajectory In Context

Segment, Associate, and Classify: Decoupled Audio-Visual Segmentation Framework