Robin Williams

bfuzzy1's activity

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

liked a Space 17 days ago

Running

Featured

71

LFM2.5 Edge Research Agent

🔬

71

Run an on-device LFM2.5 research agent with WebGPU

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

dedup: give the Gao over-optimization law one owning article

2

#650 opened about 1 month ago by

lvwerra

figures: first two wiki figures (overoptimization turnover + RLHF two-KLs pipeline)

2

#648 opened about 1 month ago by

lvwerra

new node: foundations/learning-path (the entry ramp)

2

#649 opened about 1 month ago by

lvwerra

new node: foundations/controllable-generation (de-orphans 5; the steering paradigm RLHF descends from)

2

#640 opened about 1 month ago by

lvwerra

topic: cross-link entropy-and-exploration + reasoning-emergence -> reporting-gap-audit

2

#615 opened about 1 month ago by

bfuzzy1

topic: hallucination-and-abstention developing->comprehensive (o1-card frontier weave + monitor-as-verifier; 16 anchors verified)

2

#596 opened about 1 month ago by

kshitijthakkar

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

6

#595 opened about 1 month ago by

thomwolf

upvoted 2 papers about 1 month ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 77

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 84

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

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

2

#594 opened about 1 month ago by

bfuzzy1

topic: judging-bias-and-contamination — deepen + add citations

3

#593 opened about 1 month ago by

bfuzzy1

source: arxiv:2005.01643 — Offline RL: Tutorial, Review, and Perspectives on Open Problems

2

#592 opened about 1 month ago by

bfuzzy1

source: arxiv:1910.00177 — Advantage-Weighted Regression (AWR)

2

#591 opened about 1 month ago by

bfuzzy1

source: arxiv:2006.04779 — Conservative Q-Learning for Offline Reinforcement Learning

3

#590 opened about 1 month ago by

bfuzzy1

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

2

#589 opened about 1 month ago by

bfuzzy1

source: arxiv:1707.01495 — Hindsight Experience Replay

2

#588 opened about 1 month ago by

bfuzzy1

topic: kl-regularization — build out from stub

2

#587 opened about 1 month ago by

bfuzzy1

source: arxiv:2004.07219 — D4RL: Datasets for Deep Data-Driven Reinforcement Learning

2

#586 opened about 1 month ago by

bfuzzy1

source: arxiv:1609.05473 — SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

3

#585 opened about 1 month ago by

bfuzzy1