Zongyuan Ge

MultiHaystack: Benchmarking Multimodal Reasoning over 40K Images, Videos, and Documents

StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding

PRISM: Progressive Robust Learning for Open-World Continual Category Discovery

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning

It Hears, It Sees too: Multi-Modal LLM for Depression Detection By Integrating Visual Understanding into Audio Language Models

Decoding Causal Structure: End-to-End Mediation Pathways Inference

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

UniViT: Unifying Image and Video Understanding in One Vision Encoder

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

MONICA: Benchmarking on Long-tailed Medical Image Classification

SynFER: Towards Boosting Facial Expression Recognition with Synthesis Data