Lin Huang
xinxinling-h
·
AI & ML interests
process reward models, test-time compute, self-correction ✨
Recent Activity
liked a dataset 4 days ago
marin-community/open-thoughts-4-30k-math-qwen3-32b-annotated-32768-tokens-n8-reformatted-selfconsistency liked a dataset 4 days ago
SalutefaceAAC/chain-of-thought-reasoning-traces upvoted a paper 4 days ago
ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?Organizations
None yet