Leandro von Werra PRO

lvwerra's activity

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

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

source: url:interconnects.ai/p/q-star — The Q* hypothesis / pre-o1 PRM+search prediction (speculation)

4

#749 opened 10 days ago by

lvwerra

updated a bucket about 1 hour ago

rl-llm-wiki/rl-main-bucket

319 MB

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

source: url:yam.gift/2025/06/19/NLP/LLM-Training/2025-06-19-CISPO-and-Entropy — MiniMax-M1 CISPO reconstruction (CN, speculation)

3

#750 opened 10 days ago by

lvwerra

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

source: url:latent.space/p/willccbb — Will Brown on multi-turn/agentic RL + verifiers (practitioner transcript)

4

#788 opened 10 days ago by

lvwerra

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

source: url:syhya.github.io/posts/2025-01-27-deepseek-r1 — DeepSeek-R1 deep-dive / GRPO+KL math + o1 read-across (CN, speculation)

4

#742 opened 10 days ago by

lvwerra

updated a Space about 10 hours ago

Running

3

cowrite

✍

3

Collaborate on documents with AI agents that suggest edits

updated a dataset about 14 hours ago

HuggingAI4Engineering/cadgenbench-submissions

Viewer • Updated about 14 hours ago • 130 • 10.4k • 1

New activity in lvwerra/cowrite about 17 hours ago

References, out of three general primitives

#9 opened 1 day ago by

lvwerra

Column tabs that stay attached, and a sign-in dialog that stays centred

#7 opened 1 day ago by

lvwerra

One document at every width: narrow windows scroll, never reflow

#11 opened about 17 hours ago by

lvwerra

Recover agent polling after interruptions

#10 opened about 18 hours ago by

thomwolf

Comments are closed, not ticked off — and the sheet answers the thumb

#8 opened 1 day ago by

lvwerra

The document is a page: fixed width, folding columns, real zoom

#6 opened 1 day ago by

lvwerra

New activity in rl-llm-wiki/knowledge-base about 23 hours ago

source: url:interconnects.ai/p/openais-o3-over-optimization-is-back — o3 over-optimization / RLVR failure mode (speculation)

4

#738 opened 10 days ago by

lvwerra

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

source: url:jasonwei.net/blog/asymmetry-of-verification-and-verifiers-law — Verifier's law / asymmetry of verification (speculation)

5

#739 opened 10 days ago by

lvwerra

source: url:hub.baai.ac.cn/view/44581 — AReaL-boba QwQ-32B RL reproduction (CN, speculation)

3

#752 opened 10 days ago by

lvwerra

source: url:cnblogs.com/theseventhson/p/18699462 — cnblogs R1/GRPO reproduction (zh, speculation)

3

#724 opened 12 days ago by

lvwerra

source: url:sequoiacap.com/podcast/training-data-noam-brown — Sequoia x Noam Brown: o1 team on test-time compute as scaling axis (transcript)

4

#781 opened 10 days ago by

lvwerra

New activity in lvwerra/cowrite 1 day ago

Make agent prompt work with private Spaces

#5 opened 3 days ago by

thomwolf

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

source: url:yam.gift/2025/05/01/NLP/LLM-Training/2025-05-01-Seed-Thinking-Qwen3 — ByteDance Seed-Thinking recipe + Qwen3 read-across (CN, speculation)

3

#755 opened 10 days ago by

lvwerra