pangpangxuan

pangxuan's activity

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

upvoted 2 papers about 4 hours ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 1 day ago • 50

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents

Paper • 2604.11784 • Published 3 days ago • 114

upvoted a paper 1 day ago

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published 5 days ago • 64

upvoted 3 papers 4 days ago

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published 7 days ago • 273

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published 8 days ago • 177

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 8 days ago • 309

upvoted a paper 6 days ago

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 64

upvoted a paper 9 days ago

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published Sep 2, 2025 • 238

upvoted 3 papers 12 days ago

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published 26 days ago • 337

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Paper • 2603.29620 • Published 15 days ago • 46

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Paper • 2604.02268 • Published 14 days ago • 93

upvoted a paper 13 days ago

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published 17 days ago • 142

upvoted a paper 16 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published 20 days ago • 154

upvoted a paper 18 days ago

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published 20 days ago • 131

upvoted a paper 20 days ago

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published about 1 month ago • 423

upvoted a paper 22 days ago

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Paper • 2603.21065 • Published 24 days ago • 77

upvoted 4 papers about 1 month ago

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Paper • 2603.04597 • Published Mar 4 • 210

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published Mar 12 • 91

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published Mar 10 • 151

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published Mar 6 • 118