Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Paper • 2605.04077 • Published • 1
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 1 hour ago
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO upvoted a paper about 3 hours ago
MARBLE: Multi-Aspect Reward Balance for Diffusion RL upvoted a paper about 3 hours ago
AI Co-Mathematician: Accelerating Mathematicians with Agentic AIOrganizations
None yet
upvoted a paper about 1 hour ago
upvoted 9
papers about 3 hours ago
MARBLE: Multi-Aspect Reward Balance for Diffusion RL
Paper • 2605.06507 • Published • 28
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
Paper • 2605.06651 • Published • 1
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Paper • 2605.06130 • Published • 1
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
Paper • 2605.06638 • Published • 2
SkillOS: Learning Skill Curation for Self-Evolving Agents
Paper • 2605.06614 • Published • 2
A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
Paper • 2605.06200 • Published • 5
MiA-Signature: Approximating Global Activation for Long-Context Understanding
Paper • 2605.06416 • Published • 32
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
Paper • 2605.05724 • Published • 8
Continuous Latent Diffusion Language Model
Paper • 2605.06548 • Published • 18
upvoted a paper about 5 hours ago
upvoted 3
papers about 20 hours ago
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Paper • 2605.02913 • Published • 5
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Paper • 2604.27488 • Published • 4
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 92
upvoted a paper about 21 hours ago
upvoted 5
papers 1 day ago
Lightning Unified Video Editing via In-Context Sparse Attention
Paper • 2605.04569 • Published • 11
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
Paper • 2605.04128 • Published • 8
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
Paper • 2605.04018 • Published • 27
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
Paper • 2605.05185 • Published • 84
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
Paper • 2605.05204 • Published • 21