AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces Paper • 2608.23041 • Published Aug 24 • 64
Articulated Object Reconstruction from Rest-State Observation Paper • 2607.27749 • Published Jul 30 • 52
view article Article Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action nvidia • Jun 1 • 90
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models Paper • 2605.30161 • Published May 28 • 55
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents Paper • 2605.25535 • Published May 25 • 45