Rethinking Cross-Layer Information Routing in Diffusion Transformers
Paper • 2605.20708 • Published • 111
Maohua Li
Met4physics
AI & ML interests
GenAI
Recent Activity
upvoted a paper 28 days ago
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models new activity about 1 month ago
Wuli-art/Qwen-Image-2512-Turbo-LoRA-2-Steps:support for other qwen modelsOrganizations
submitted a
paper to Daily Papers about 1 month ago
authored 3
papers about 1 month ago
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Paper • 2605.20708 • Published • 111
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 97
Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications
Paper • 2409.03368 • Published • 1