TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

Apr 15, 2025·

Xiangyu Zeng

,

Kunchang Li

,

Chenting Wang

,

Xinhao Li

,

Tianxiang Jiang

,

Ziang Yan

,

Songze Li

,

Yansong Shi

,

Zhengrong Yue

,

Yi Wang

,

Yali Wang

,

Yu Qiao

Limin Wang

Limin Wang

· 0 min read

Type

Conference paper

Publication

The Thirteenth International Conference on Learning Representations

Last updated on Apr 15, 2025

Limin Wang

Authors

Nanjing University

← SPA: 3D Spatial-Awareness Enables Effective Embodied Representation Apr 15, 2025