Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
Paper • 2605.06241 • Published • 3
Marie-Claire Dupont
acc-1234
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 24 hours ago
Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning liked a model 11 days ago
BAAI/bge-m3 liked a model 19 days ago
ruygar/gemma-4-E2B-it-BBOrganizations
None yet
upvoted a paper about 24 hours ago
upvoted a paper 29 days ago
upvoted a paper about 1 month ago
upvoted 3
papers about 2 months ago
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 311
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions
Paper • 2603.15612 • Published • 153
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Paper • 2603.04597 • Published • 210
upvoted 2
papers 2 months ago
upvoted 8
papers 3 months ago
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Paper • 2602.08354 • Published • 264
A Very Big Video Reasoning Suite
Paper • 2602.20159 • Published • 523
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 220
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
Paper • 2602.12783 • Published • 216
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents
Paper • 2602.07274 • Published • 210
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs
Paper • 2602.10388 • Published • 244
NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control
Paper • 2602.09070 • Published • 46
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies
Paper • 2602.09877 • Published • 197
upvoted an article 3 months ago
Article
Codex 正在推动 AI 模型的开源与训练流程
burtenshaw, evalstate
• • 13