siyeng feng

siyengfeng's activity

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

upvoted 12 papers 5 days ago

MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

Paper • 2604.08516 • Published about 1 month ago • 43

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

Paper • 2604.13016 • Published 26 days ago • 90

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

Paper • 2604.11784 • Published 27 days ago • 143

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Paper • 2604.14164 • Published Mar 23 • 35

Near-Future Policy Optimization

Paper • 2604.20733 • Published 18 days ago • 74

Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora

Paper • 2604.24819 • Published 13 days ago • 87

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published 12 days ago • 261

Large Language Models Explore by Latent Distilling

Paper • 2604.24927 • Published 13 days ago • 72

RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments

Paper • 2604.26067 • Published 12 days ago • 73

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Paper • 2604.26752 • Published 11 days ago • 102

Co-Evolving Policy Distillation

Paper • 2604.27083 • Published 11 days ago • 63

Heterogeneous Scientific Foundation Model Collaboration

Paper • 2604.27351 • Published 10 days ago • 208

upvoted 5 papers 26 days ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 235

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published about 1 month ago • 289

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published about 1 month ago • 262

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published about 1 month ago • 245

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

Paper • 2604.07430 • Published Apr 8 • 187

upvoted a paper about 2 months ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published Mar 17 • 139

upvoted an article 6 months ago

view article

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

• 
• 
• +2

Feb 4, 2025

•

192

upvoted a paper 9 months ago

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4, 2025 • 275