The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents Paper • 2608.06065 • Published 7 days ago • 7
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models Paper • 2607.28609 • Published 14 days ago • 70
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 7 days ago • 46
NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap Paper • 2608.04397 • Published 8 days ago • 23
MiniWorld: Democratizing the Training of Video World Models from Scratch Paper • 2608.01127 • Published 11 days ago • 19
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction Paper • 2607.29677 • Published 13 days ago • 23