5 papers
EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning
Yogesh Kulkarni, Pooyan Fazli
Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal large language models (MLLMs) stru…
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
Chaoyu Li, Yogesh Kulkarni, Pooyan Fazli
The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference v…
AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video
Yogesh Kulkarni, Pooyan Fazli
Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Re…
VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment
Yogesh Kulkarni, Pooyan Fazli
Video-language models (Video-LLMs) excel at understanding video content but struggle with spatial relationships, temporal ordering, and cross-frame continuity. To address these lim…
VideoSAVi: Self-Aligned Video Language Models without Human Supervision
Yogesh Kulkarni, Pooyan Fazli
Recent advances in video-large language models (Video-LLMs) have led to significant progress in video understanding. Current preference optimization methods often rely on proprieta…