EgoExoBench: a benchmark for first-and third-person view video understanding in MLLMs

Oct 11, 2025·

Yuping He

,

Yifei Huang

,

Guo Chen

,

Baoqi Pei

,

Jilan Xu

Tong Lu

Tong Lu

,

Jiangmiao Pang

· 0 min read

Cite URL

Type

Conference paper

Publication

Proceedings of the Neural Information Processing Systems

Last updated on Oct 11, 2025

Tong Lu

Authors

Nanjing University

← Eagle 2.5: boosting long-context post-training for frontier vision-language models Oct 11, 2025

Gated integration of low-rank adaptation for continual learning of language models Oct 11, 2025 →