SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture Paper • 2605.12500 • Published 4 days ago • 167
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 161
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published Apr 6 • 235
MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction Paper • 2603.19231 • Published Mar 19 • 36
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer Paper • 2603.19227 • Published Mar 19 • 42
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation Paper • 2603.16669 • Published Mar 17 • 70
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation Paper • 2603.16669 • Published Mar 17 • 70
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation Paper • 2603.16669 • Published Mar 17 • 70 • 4
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions Paper • 2603.15612 • Published Mar 16 • 153