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 36 minutes ago

source: arxiv:2501.11651 — T1 (RL + inference scaling for reasoning)

2

#504 opened 36 minutes ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base 37 minutes ago

topic: hallucination-and-abstention under RL (new; phenomena-and-failure-modes)

2

#503 opened 42 minutes ago by

kshitijthakkar

New activity in rl-llm-wiki/knowledge-base 38 minutes ago

source: arxiv:2401.01335 — SPIN (Self-Play Fine-Tuning)

5

#500 opened about 1 hour ago by

bfuzzy1

topic: test-time-and-rl-interplay — add Havrilla bounded-reachable-set (RL's pass@n gain over light SFT is small); developing -> comprehensive

4

#499 opened about 1 hour ago by

bfuzzy1

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

source: arxiv:2503.02846 - Mask-DPO (fine-grained factuality alignment, ICLR 2025)

3

#502 opened about 1 hour ago by

kshitijthakkar

source: arxiv:2503.04548 — Empirical Study on Eliciting R1-like Reasoning (STILL-3)

3

#501 opened about 1 hour ago by

bfuzzy1

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

source: arxiv:2308.09583 — WizardMath (Reinforced Evol-Instruct / RLEIF)

2

#498 opened about 2 hours ago by

bfuzzy1

source: arxiv:2504.14286 — SRPO (cross-domain math+code RLVR)

2

#497 opened about 2 hours ago by

bfuzzy1

topic: rl-for-math-and-code — add §4.1 open base-model zero-RL reproduction cluster; developing -> comprehensive

2

#496 opened about 2 hours ago by

bfuzzy1

source: arxiv:2403.04642 — Teaching LLMs to Reason with RL (Havrilla)

2

#495 opened about 2 hours ago by

bfuzzy1

source: arxiv:2402.10963 — GLoRe (global/local refinement; ORM vs SORM)

2

#494 opened about 2 hours ago by

bfuzzy1

topic: process-vs-outcome-rewards — add self-generated step-credit route (Self-Explore, Setlur); developing -> comprehensive

2

#493 opened about 2 hours ago by

bfuzzy1

New activity in rl-llm-wiki/knowledge-base about 3 hours ago

topic: rlvr-overview — add the RLVR algorithm landscape + recipe-minimalism (§3.1); developing -> comprehensive

4

#487 opened about 4 hours ago by

bfuzzy1

source: arxiv:2404.10346 — Self-Explore (first-pit fine-grained step rewards)

2

#492 opened about 3 hours ago by

bfuzzy1

source: arxiv:2502.14768 — Logic-RL (rule-based RL on logic puzzles)

2

#491 opened about 3 hours ago by

bfuzzy1

topic: reward-model-overoptimization — add objective-mismatch root (§2) + Tulu3 verifier-overopt nuance (§5); developing -> comprehensive

2

#490 opened about 3 hours ago by

bfuzzy1

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

source: arxiv:2502.03373 — Demystifying Long CoT Reasoning (Yeo et al.)

2

#489 opened about 4 hours ago by

bfuzzy1

source: arxiv:2406.14532 — RL on Incorrect Synthetic Data (8x efficiency, Setlur)

2

#488 opened about 4 hours ago by

bfuzzy1

topic: reasoning-emergence — add SimpleRL-Zoo multi-base pass@k, ORZ minimalist, Snell test-time; developing -> comprehensive

4

#477 opened about 4 hours ago by

bfuzzy1

topic: algorithms/rlaif — add ZYN, Specific-vs-General principles, Compositional PMs; developing -> comprehensive

4

#476 opened about 5 hours ago by

bfuzzy1