Huiyu Wang

5

Papers

40

Total Citations

Papers (5)

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

NeurIPS 2025arXiv

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

Learning to Segment Referred Objects from Narrated Egocentric Videos

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation