Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models Paper • 2604.27124 • Published 11 days ago • 10
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors Paper • 2605.00658 • Published 9 days ago • 80
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling Paper • 2604.23586 • Published 14 days ago • 2
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models Paper • 2605.00414 • Published 9 days ago • 7
Map2World: Segment Map Conditioned Text to 3D World Generation Paper • 2605.00781 • Published 9 days ago • 24
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills Paper • 2604.24026 • Published 13 days ago • 19
Learning while Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies Paper • 2605.00416 • Published 9 days ago • 11
Heterogeneous Scientific Foundation Model Collaboration Paper • 2604.27351 • Published 10 days ago • 208
PhyCo: Learning Controllable Physical Priors for Generative Motion Paper • 2604.28169 • Published 10 days ago • 13
World2Minecraft: Occupancy-Driven Simulated Scenes Construction Paper • 2604.27578 • Published 10 days ago • 4
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons Paper • 2604.28130 • Published 10 days ago • 22
UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards Paper • 2604.14967 • Published 24 days ago • 15
TissUnet: Improved Extracranial Tissue and Cranium Segmentation for Children through Adulthood Paper • 2506.05660 • Published Jun 6, 2025 • 1
Target-Oriented Pretraining Data Selection via Neuron-Activated Graph Paper • 2604.15706 • Published 23 days ago • 10
UniMesh: Unifying 3D Mesh Understanding and Generation Paper • 2604.17472 • Published 21 days ago • 11