pangpangxuan

pangxuan's activity

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

upvoted 2 papers 1 day ago

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Paper • 2605.31264 • Published 5 days ago • 92

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Paper • 2605.31584 • Published 5 days ago • 37

upvoted 2 papers 3 days ago

Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning

Paper • 2605.28424 • Published 7 days ago • 28

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Paper • 2605.29801 • Published 6 days ago • 137

upvoted a paper 8 days ago

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

Paper • 2605.25874 • Published 9 days ago • 101

upvoted 3 papers 12 days ago

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

Paper • 2605.19833 • Published 15 days ago • 131

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Paper • 2605.14678 • Published 15 days ago • 102

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

Paper • 2605.14747 • Published 20 days ago • 145

upvoted 2 papers 13 days ago

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published 22 days ago • 195

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond

Paper • 2605.19660 • Published 15 days ago • 40

upvoted a paper 14 days ago

Code as Agent Harness

Paper • 2605.18747 • Published 16 days ago • 211

upvoted a paper 16 days ago

MMSkills: Towards Multimodal Skills for General Visual Agents

Paper • 2605.13527 • Published 20 days ago • 118

upvoted 2 papers 19 days ago

Self-Distilled Agentic Reinforcement Learning

Paper • 2605.15155 • Published 20 days ago • 111

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Paper • 2605.13301 • Published 21 days ago • 159

upvoted 5 papers 20 days ago

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

Paper • 2605.13037 • Published 21 days ago • 8

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

Paper • 2605.10780 • Published 22 days ago • 33

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

Paper • 2605.10899 • Published 23 days ago • 77

δ-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published 22 days ago • 125

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

Paper • 2603.16871 • Published Mar 17 • 61

upvoted a paper 21 days ago

OpenGame: Open Agentic Coding for Games

Paper • 2604.18394 • Published Apr 20 • 81