Tushar Nagarajan

Researcher@FAIR·美国·OpenReview

研究方向

attributes · compositionality · affordances · human object interaction · egocentric video · procedural video · instructional video · long video · video LLMs

4.0

Latent Action Robot Foundation World Models for Cross-Embodiment Adaptation

ICLR 2026Rejected

9.1

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

NeurIPS 2025Spotlight

6.0

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

ICLR 2025Poster

二作

5.8

Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning

合作者 (20)

Christoph Feichtenhofer

Hanoona Abdul Rasheed

1 篇