Thomas Wolf PRO

thomwolf's activity

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

New activity in rl-llm-wiki/rl-wiki 3 days ago

Search inside article bodies from the top-left box; ⌘K focuses it

#2 opened 9 days ago by

thomwolf

New activity in rl-llm-wiki/knowledge-base 4 days ago

source: arxiv:2412.16339 — Deliberative Alignment (Reasoning Enables Safer LMs)

6

#595 opened 4 days ago by

thomwolf

New activity in rl-llm-wiki/knowledge-base 5 days ago

source: arxiv:2412.16720 — OpenAI o1 System Card

2

#580 opened 5 days ago by

bfuzzy1

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

2

#579 opened 5 days ago by

bfuzzy1

source: arxiv:2404.19733 — Iterative Reasoning Preference Optimization

2

#577 opened 5 days ago by

bfuzzy1

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

2

#576 opened 5 days ago by

bfuzzy1

topic: entropy-and-exploration — deepen to comprehensive

2

#582 opened 5 days ago by

bfuzzy1

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

2

#594 opened 5 days ago by

bfuzzy1

topic: kl-regularization — build out from stub

2

#587 opened 5 days ago by

bfuzzy1

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

4

#567 opened 6 days ago by

bfuzzy1

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

2

#589 opened 5 days ago by

bfuzzy1

topic: reward-hacking — deepen to comprehensive

2

#578 opened 5 days ago by

bfuzzy1

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

2

#569 opened 6 days ago by

bfuzzy1

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

2

#565 opened 6 days ago by

bfuzzy1

source: arxiv:2206.02336 — DIVERSE step-aware verifier

2

#571 opened 6 days ago by

bfuzzy1

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

2

#566 opened 6 days ago by

bfuzzy1

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

2

#568 opened 6 days ago by

bfuzzy1

source: arxiv:2209.15189 — Learning by Distilling Context

2

#570 opened 6 days ago by

bfuzzy1

source: OAuth scope validation 6d57c493

1

#575 opened 5 days ago by

thomwolf

source: OAuth scope validation 755d426a

1

#574 opened 5 days ago by

thomwolf