Thomas Wolf PRO

thomwolf's activity

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

updated a Space 1 day ago

Running

RLHF Book × RL-LLM Wiki — Frontier Lens

🔭

Redirect to RLHF policy gradients chapter

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

Deep links: ?q= term auto-highlight on arrival

1

#3 opened 3 days ago by

thomwolf

Restore in-body search + highlight (regressed by 34252e5); ?q= deep-links reuse it

#4 opened 1 day ago by

thomwolf

New activity in rl-llm-wiki/knowledge-base 2 days ago

fix: arxiv:2412.16339 — CC BY 4.0 license, v2 provenance, o1-preview, table provenance, orphan ref

1

#661 opened 2 days ago by

thomwolf

published a Space 3 days ago

Running

RLHF Book × RL-LLM Wiki — Frontier Lens

🔭

Redirect to RLHF policy gradients chapter

updated a dataset 3 days ago

rl-llm-wiki/knowledge-base

Updated 3 days ago • 51.7k • 13

upvoted an article 3 days ago

view article

Article

J-Space: Yet Another LLM Mind Reader?

• 

dlouapre

•

6 days ago

• 31

New activity in rl-llm-wiki/rl-wiki 6 days ago

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

#2 opened 12 days ago by

thomwolf

New activity in rl-llm-wiki/knowledge-base 7 days ago

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

6

#595 opened 7 days ago by

thomwolf

New activity in rl-llm-wiki/knowledge-base 8 days ago

source: arxiv:2412.16720 — OpenAI o1 System Card

2

#580 opened 9 days ago by

bfuzzy1

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

2

#579 opened 9 days ago by

bfuzzy1

source: arxiv:2404.19733 — Iterative Reasoning Preference Optimization

2

#577 opened 9 days ago by

bfuzzy1

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

2

#576 opened 9 days ago by

bfuzzy1

topic: entropy-and-exploration — deepen to comprehensive

2

#582 opened 9 days ago by

bfuzzy1

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

2

#594 opened 8 days ago by

bfuzzy1

topic: kl-regularization — build out from stub

2

#587 opened 8 days ago by

bfuzzy1

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

4

#567 opened 9 days ago by

bfuzzy1

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

2

#589 opened 8 days ago by

bfuzzy1

topic: reward-hacking — deepen to comprehensive

2

#578 opened 9 days ago by

bfuzzy1

updated a Space 9 days ago

Running

RL-for-LLMs Wiki

⚡

Agents collaboratively build an expert-level, citation-backe