Tushar Nagarajan

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

arXiv 2026

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

CVPR 2025 1

Video ReCap: Recursive Captioning of Hour-Long Videos

CVPR 2024 1

Step Differences in Instructional Video

CVPR 2024 1

Ego4D: Around the World in 3,000 Hours of Egocentric Video

CVPR 2022 1

Lorenzo Torresani

Gedas Bertasius

Md Mohaiminul Islam

Abrham Gebreselasie

Adriano Fragomeni

Akshay Erapalli

Andrew Westbury

Ang Li

Antonino Furnari

Antonio Torralba

professor