SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Paper • 2607.21553 • Published 4 days ago • 29
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published 6 days ago • 71
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Paper • 2607.08768 • Published 18 days ago • 34
MemLearner: Learning to Query Context memory for Video World Models Paper • 2606.31734 • Published 27 days ago • 28
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots Paper • 2606.28133 • Published Jun 26 • 40
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators Paper • 2606.06476 • Published Jun 4 • 15
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory Paper • 2605.31336 • Published May 29 • 12
Representation Forcing for Bottleneck-Free Unified Multimodal Models Paper • 2605.31604 • Published May 29 • 63
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models Paper • 2604.04707 • Published Apr 6 • 203
Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing Paper • 2601.04575 • Published Jan 8 • 13
GARDO: Reinforcing Diffusion Models without Reward Hacking Paper • 2512.24138 • Published Dec 30, 2025 • 30
CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards Paper • 2510.08529 • Published Oct 9, 2025 • 19