arxiv:2605.20708
Maohua Li
Met4physics
AI & ML interests
GenAI
Recent Activity
upvoted a paper about 21 hours ago
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps authored a paper 1 day ago
Rethinking Cross-Layer Information Routing in Diffusion Transformers authored a paper 2 days ago
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps