arxiv:2503.12769
Yi-Xing Peng
maybetomorrow
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
8 days ago
Architecture Decoupling Is Not All You Need For Unified Multimodal Model
authored
a paper
9 months ago
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining
authored
a paper
9 months ago
ViSpeak: Visual Instruction Feedback in Streaming Videos