小林優奈
lincoln-smith
AI & ML interests
Alignment-focused model research. Sharing reproducible results.
Recent Activity
upvoted a paper about 21 hours ago
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts upvoted a paper about 23 hours ago
ReSyn: A Generalized Recursive Regular Expression Synthesis Framework upvoted a paper 1 day ago
Looped World ModelsOrganizations
None yet