Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
Paper
• 2511.08577 • Published
• 108
Yichen You
youyc22
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
How Far Can Unsupervised RLVR Scale LLM Training? liked
a dataset about 2 months ago
Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b published
a model 2 months ago
nics-efc/Standard-1.7B Organizations
authored a paper 4 months ago