🔄 In a Training Loop

quinn

jwhe

·

AI & ML interests

None yet

Recent Activity

authored a paper 4 days ago

SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation

authored a paper 4 days ago

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

authored a paper 4 days ago

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

View all activity

Organizations

upvoted 2 papers 5 days ago

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Paper • 2609.38847 • Published 19 days ago • 71

SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation

Paper • 2608.03092 • Published Aug 4 • 9

upvoted a paper 3 months ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published Jul 28 • 42

upvoted a paper 8 months ago

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published Feb 13 • 68

upvoted a paper almost 3 years ago

TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise

Paper • 2310.19019 • Published Oct 29, 2023 • 9