LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory Paper • 2603.03269 • Published 22 days ago • 61
UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data Paper • 2603.05312 • Published 20 days ago • 7
VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning Paper • 2510.08555 • Published Oct 9, 2025 • 65
ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents Paper • 2507.22827 • Published Jul 30, 2025 • 101