https://arxiv.org/abs/2505.22888
ds - means continue post-training on deepseek distilled qwen math 7b
limo-{language}-{amount of data}
Shan Chen
shanchen
AI & ML interests
I train and eval pretty ok
Recent Activity
upvoted a paper 24 days ago
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning updated
a dataset about 1 month ago
AIM-Harvard/TrialPanorama-filtered published
a dataset about 1 month ago
AIM-Harvard/TrialPanorama-filtered Organizations
