arxiv:2605.20035
Zijie Xin
xxayt
ยท
AI & ML interests
multi-modal learning, AIGC
Recent Activity
upvoted a paper 2 days ago
Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search commentedon a paper 8 days ago
Stage-adaptive Token Selection for Efficient Omni-modal LLMs upvoted a paper 8 days ago
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language ModelsOrganizations
