Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Paper • 2604.02288 • Published • 31
charliezhang
Clockz
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing upvoted a paper about 15 hours ago
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space updated a model 9 days ago
Interplay-LM-Reasoning/extrapolation_midtrainOrganizations
upvoted a paper about 2 hours ago
upvoted a paper about 15 hours ago
upvoted a paper 25 days ago
upvoted a paper 28 days ago
upvoted 4
papers about 1 month ago
Utonia: Toward One Encoder for All Point Clouds
Paper • 2603.03283 • Published • 185
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 194
SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
Paper • 2602.23866 • Published • 88
MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning
Paper • 2603.02024 • Published • 47
upvoted 4
papers about 2 months ago
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Paper • 2602.08354 • Published • 263
Imagination Helps Visual Reasoning, But Not Yet in Latent Space
Paper • 2602.22766 • Published • 44
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation
Paper • 2602.18283 • Published • 56
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper • 2602.05400 • Published • 352
upvoted 3
papers 3 months ago
Reinforcement Learning via Self-Distillation
Paper • 2601.20802 • Published • 43
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation
Paper • 2601.21420 • Published • 42
Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind
Paper • 2601.15715 • Published • 14
upvoted 4
papers 4 months ago
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Paper • 2512.19673 • Published • 66
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 106
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
Paper • 2512.07783 • Published • 39
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
Paper • 2512.04324 • Published • 159
upvoted a paper 6 months ago