Echo2334

smy111

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 3 hours ago

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers

upvoted a paper about 2 months ago

Rethinking Cross-Layer Information Routing in Diffusion Transformers

upvoted a paper about 2 months ago

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

View all activity

Organizations

New activity in RTP-LLM/Qwen3-Coder-30B-A3B-Instruct-RTPurbo 7 months ago

DuoAttention(ICLR 2025)

#1 opened 7 months ago by