Robin Williams

bfuzzy1's activity

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

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

source: arxiv:2304.05128 — Teaching LLMs to Self-Debug (rubber-duck + execution feedback)

5

#555 opened 1 day ago by

thomwolf

source: arxiv:2305.00944 - Poisoning instruction tuning

2

#562 opened 1 day ago by

lewtun

source: arxiv:2311.09724 — OVM (Outcome-supervised Value Models for planning)

2

#563 opened 1 day ago by

bfuzzy1

source: arxiv:2309.17179 — TS-LLM (AlphaZero-like tree search guides LLM decoding & training)

2

#561 opened 1 day ago by

bfuzzy1

source: arxiv:2410.04343 — Inference Scaling for Long-Context RAG (DRAG / IterDRAG)

2

#560 opened 1 day ago by

bfuzzy1

source: arxiv:2406.03816 — ReST-MCTS* (process-reward-guided self-training)

2

#559 opened 1 day ago by

bfuzzy1

source: arxiv:2211.10435 — PAL (Program-aided Language Models)

1

#558 opened 1 day ago by

bfuzzy1

source: arxiv:2402.02658 — MiPS (model-induced process supervision)

2

#557 opened 1 day ago by

bfuzzy1

topic: agentic-and-tool-use-rl — deepen to comprehensive (landscape table, retrieval sub-family, credit-assignment, reward-hacking; promote cites to anchors)

2

#556 opened 1 day ago by

bfuzzy1

topic: harmlessness-and-refusals — add runnable check (Safe-RLHF PPO-Lagrangian constraint) + maturity->comprehensive

4

#550 opened 1 day ago by

bfuzzy1

topic: overoptimization-and-mode-collapse — add runnable check (Gao proxy-up/gold-peaks-then-falls) + maturity->comprehensive

4

#551 opened 1 day ago by

bfuzzy1

source: arxiv:2305.06983 — FLARE (Forward-Looking Active Retrieval)

4

#546 opened 1 day ago by

bfuzzy1

source: arxiv:2310.11511 — Self-RAG (retrieve/generate/critique via reflection tokens)

4

#542 opened 1 day ago by

bfuzzy1

source: arxiv:2406.14283 — Q* (deliberative planning for multi-step reasoning)

4

#541 opened 1 day ago by

bfuzzy1

topic: credit-granularity — add runnable check (seq==token broadcast under terminal reward; diverge when per-token) + maturity->comprehensive

2

#553 opened 1 day ago by

bfuzzy1

topic: rl-for-llms-overview — add runnable check (KL-regularized Boltzmann optimum) + maturity->comprehensive

2

#552 opened 1 day ago by

bfuzzy1

topic: async-and-off-policy-rl — add runnable check (IS unbiasedness + clip bias) + maturity->comprehensive

2

#549 opened 1 day ago by

bfuzzy1

topic: mdp-formulation — add runnable check (token-level MDP == sequence bandit under terminal reward)

2

#548 opened 1 day ago by

bfuzzy1

fix: de-anchor 17 dangling [source:] citations across 12 source files (corpus hygiene)

2

#547 opened 1 day ago by

bfuzzy1

source: arxiv:2406.06592 — OmegaPRM (automated process supervision)

2

#545 opened 1 day ago by

bfuzzy1