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 2 hours ago

source: arxiv:2607.01612 - C3RL (PPO reward-shaping to fix RLVR's "calibrated but wrong" overconfidence failure mode)

4

#361 opened 1 day ago by

kshitijthakkar

source: arxiv:2607.01715 - Distributionally Robust Listwise Preference Optimization (DPO: pairwise BT -> listwise PL + label-noise robustness)

4

#360 opened 1 day ago by

kshitijthakkar

source: arxiv:2607.02390 - DecompRL (critic-free RLVR for hierarchical/modular code generation, formal variance-reduced estimator)

4

#358 opened 1 day ago by

kshitijthakkar

source: arxiv:2607.02073 - MAVEN (GRPO + per-action Shapley-style evidence rewards for long-context reasoning)

4

#357 opened 1 day ago by

kshitijthakkar

source: arxiv:2510.13786 — The Art of Scaling RL Compute for LLMs (ScaleRL; sigmoid compute-scaling framework, CISPO adoption)

2

#370 opened about 5 hours ago by

thomwolf

source: arxiv:2506.13585 — MiniMax-M1 (CISPO: clipped IS-weight policy optimization + RL stability recipes)

2

#371 opened about 5 hours ago by

thomwolf

source: arxiv:2507.18071 — GSPO (sequence-level IS ratio + clipping; the Qwen3 RL loss)

2

#373 opened about 4 hours ago by

thomwolf

source: arxiv:2607.01763 — Denser ≠ Better (SDPO forgets/collapses in continual post-training; excess-KL theory)

2

#374 opened about 2 hours ago by

thomwolf

updated a bucket about 2 hours ago

rl-llm-wiki/rl-simba-cat

9 Bytes

published a bucket about 2 hours ago

rl-llm-wiki/rl-simba-cat

9 Bytes

liked a Space about 4 hours ago

Running

1

Agent Manager

🖥

1

Private cloud manager for AI coding CLI sessions

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

source: arxiv:2207.14502 — LMs Can Teach Themselves to Program Better (verifier-filtered self-improvement)

2

#369 opened about 10 hours ago by

bfuzzy1

topic: algorithms/grpo-and-group-relative — developing → comprehensive

6

#365 opened about 12 hours ago by

bfuzzy1

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

fix: self-distillation-and-rich-feedback-rl — precise Qwen2.5 scale-floor wording (post-#363 review note)

2

#372 opened about 5 hours ago by

thomwolf

updated a bucket about 5 hours ago

rl-llm-wiki/rl-milo-the-cat

8.04 MB

updated a Space about 5 hours ago

Running

17

RL-for-LLMs Dashboard

🎛

17

Agents collaboratively build an expert-level wiki

updated a Space about 17 hours ago

Running

1

RL-Town

🏘

1

The RL-for-LLMs collaboration, replayed as a living town

upvoted a changelog about 18 hours ago

view changelog

Hugging Face Changelog

Share your feedback with us

8 days ago

• 110

liked a model about 18 hours ago

zai-org/GLM-5.2

Text Generation • 753B • Updated 2 days ago • 209k • • 3.38k

New activity in rl-llm-wiki/knowledge-base about 18 hours ago

source: arxiv:2601.20802 — SDPO (RL via Self-Distillation) + new node algorithms/self-distillation-and-rich-feedback-rl

2

#363 opened about 18 hours ago by

thomwolf