Pan Wang

wangpan-ustc's activity

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

authored a paper about 12 hours ago

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 4 days ago • 346

upvoted a paper about 18 hours ago

ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning

Paper • 2610.18683 • Published 4 days ago • 25

upvoted a paper about 19 hours ago

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 4 days ago • 346

authored a paper 1 day ago

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper • 2610.33568 • Published 5 days ago • 364

upvoted a paper 2 days ago

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper • 2610.33568 • Published 5 days ago • 364

upvoted a paper 6 days ago

Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents

Paper • 2610.26233 • Published 10 days ago • 36

authored a paper 8 days ago

PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

Paper • 2610.27628 • Published 9 days ago • 168

upvoted a paper 8 days ago

PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

Paper • 2610.27628 • Published 9 days ago • 168

authored a paper 10 days ago

BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

Paper • 2610.20424 • Published 15 days ago • 499

upvoted a paper 10 days ago

BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

Paper • 2610.20424 • Published 15 days ago • 499

upvoted a paper 13 days ago

UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

Paper • 2610.09823 • Published 22 days ago • 199

authored 2 papers about 1 month ago

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction

Paper • 2608.11772 • Published Aug 12 • 4

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published Sep 4 • 119

upvoted 2 papers about 1 month ago

CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion

Paper • 2606.30030 • Published Jun 29 • 6

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published Sep 4 • 119

liked a dataset about 2 months ago

ant-intl/DeveloperSkills-Code2Skill

Updated Aug 21 • 336 • 18

upvoted a paper about 2 months ago

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction

Paper • 2608.11772 • Published Aug 12 • 4

upvoted a paper 2 months ago

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

Paper • 2608.13622 • Published Aug 13 • 17

authored 2 papers 2 months ago

AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents

Paper • 2605.17933 • Published May 18 • 30

SEAL: Synergistic Co-Evolution of Agents and Learning Environments

Paper • 2605.24426 • Published May 23 • 10