UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations Paper • 2608.15930 • Published 5 days ago • 43
Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation Paper • 2606.08719 • Published Jun 7
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations Paper • 2608.15930 • Published 5 days ago • 43
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 132
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published Apr 9 • 294
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Paper • 2603.22212 • Published Mar 23 • 127
Video-CoE: Reinforcing Video Event Prediction via Chain of Events Paper • 2603.14935 • Published Mar 16 • 90
Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing Paper • 2603.03143 • Published Mar 3 • 144
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing Paper • 2603.00141 • Published Feb 24 • 137
MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios Paper • 2602.22638 • Published Feb 26 • 106
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation Paper • 2602.18283 • Published Feb 20 • 57
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation Paper • 2602.18283 • Published Feb 20 • 57