Richard Lee
lixin4sky
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps new activity 9 months ago
deepseek-ai/DeepSeek-V3.2-Exp:能不能一直保留旧版的deepseek v3.1的API接口? liked a model about 1 year ago
deepseek-ai/DeepSeek-Prover-V2-671B