Thomas Wolf PRO

thomwolf's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in rl-llm-wiki/knowledge-base about 9 hours ago

source: arxiv:2412.16720 — OpenAI o1 System Card

2

#580 opened about 18 hours ago by

bfuzzy1

source: arxiv:2402.00658 — Learning Planning-based Reasoning via Trajectories Collection and Process Reward Synthesizing

2

#579 opened about 18 hours ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 11 hours ago

source: arxiv:2404.19733 — Iterative Reasoning Preference Optimization

2

#577 opened about 18 hours ago by

bfuzzy1

source: arxiv:2403.17031 — The N+ Implementation Details of RLHF with PPO (TL;DR Summarization)

2

#576 opened about 18 hours ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 13 hours ago

topic: entropy-and-exploration — deepen to comprehensive

2

#582 opened about 18 hours ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 15 hours ago

topic: policy-gradient-methods — deepen + add citations

2

#594 opened about 17 hours ago by

bfuzzy1

topic: kl-regularization — build out from stub

2

#587 opened about 18 hours ago by

bfuzzy1

topic: test-time-and-rl-interplay — deepen to comprehensive

4

#567 opened 1 day ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 17 hours ago

topic: preference-reward-models — deepen + bump to comprehensive

2

#589 opened about 18 hours ago by

bfuzzy1

topic: reward-hacking — deepen to comprehensive

2

#578 opened about 18 hours ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 21 hours ago

source: arxiv:2307.04408 — Teaching LLMs to Translate with Comparison (TIM)

2

#569 opened 1 day ago by

bfuzzy1

source: arxiv:2210.03350 — Measuring and Narrowing the Compositionality Gap in Language Models (Self-Ask)

2

#565 opened 1 day ago by

bfuzzy1

source: arxiv:2206.02336 — DIVERSE step-aware verifier

2

#571 opened 1 day ago by

bfuzzy1

topic: process-vs-outcome-rewards — deepen to comprehensive

2

#566 opened 1 day ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 24 hours ago

source: arxiv:2310.04373 — Confronting Reward Model Overoptimization with Constrained RLHF

2

#568 opened 1 day ago by

bfuzzy1

source: arxiv:2209.15189 — Learning by Distilling Context

2

#570 opened 1 day ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base 1 day ago

source: OAuth scope validation 6d57c493

1

#575 opened 1 day ago by

thomwolf

source: OAuth scope validation 755d426a

1

#574 opened 1 day ago by

thomwolf

source: arxiv:2607.04364 — RL Forgets! / CPO (RL still forgets under contamination-controlled continual learning; KL-locus diagnosis)

2

#573 opened 1 day ago by

thomwolf

topic: self-distillation-and-rich-feedback-rl — developing → comprehensive (variants map + GKD/MiniLLM lineage)

4

#572 opened 1 day ago by

thomwolf