Jing Bi

5

Papers

47

Total Citations

Papers (5)

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

ZeroSep: Separate Anything in Audio with Zero Training

Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach