arxiv:2510.06751
Junhan ZHU
Alrightlone
AI & ML interests
Efficient AI
Recent Activity
upvoted
a
paper
5 minutes ago
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
upvoted
a
paper
21 days ago
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal
Understanding
upvoted
a
paper
27 days ago
VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
Organizations
None yet