pangpangxuan

pangxuan's activity

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

upvoted a paper about 19 hours ago

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning

Paper • 2605.13037 • Published 2 days ago • 4

upvoted 8 papers 1 day ago

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization

Paper • 2605.10780 • Published 3 days ago • 31

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Paper • 2605.10899 • Published 4 days ago • 70

δ-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published 3 days ago • 99

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Paper • 2603.16871 • Published Mar 17 • 61

OpenGame: Open Agentic Coding for Games

Paper • 2604.18394 • Published 25 days ago • 80

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Paper • 2604.08364 • Published Apr 9 • 101

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

Paper • 2604.07429 • Published Apr 8 • 121

Self-Distilled RLVR

Paper • 2604.03128 • Published Apr 3 • 173

upvoted 4 papers 3 days ago

A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping

Paper • 2605.06200 • Published 8 days ago • 14

Rubric-based On-policy Distillation

Paper • 2605.07396 • Published 7 days ago • 37

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published 4 days ago • 103

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

Paper • 2605.06139 • Published 8 days ago • 64

upvoted 2 papers 6 days ago

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Paper • 2605.06130 • Published 8 days ago • 104

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 12 days ago • 102

upvoted 2 papers 7 days ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published 14 days ago • 47

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Paper • 2605.05204 • Published 9 days ago • 25

upvoted a paper 10 days ago

Co-Evolving Policy Distillation

Paper • 2604.27083 • Published 16 days ago • 64

upvoted a paper 19 days ago

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

Paper • 2604.20987 • Published 23 days ago • 21

upvoted a paper 22 days ago

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Paper • 2604.13602 • Published 30 days ago • 32