Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory Paper • 2608.29910 • Published 2 days ago
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback Paper • 2608.30241 • Published 1 day ago • 3
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability Paper • 2608.30320 • Published 1 day ago • 9
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation Paper • 2608.30396 • Published 1 day ago • 1
BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives Paper • 2608.31113 • Published 1 day ago • 1
Rubric-to-Code Credit Assignment for Reinforcement Learning Paper • 2608.27906 • Published 4 days ago • 5
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution Paper • 2608.27454 • Published 5 days ago • 24
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher Paper • 2608.26872 • Published 5 days ago • 75
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans Paper • 2608.24909 • Published Jul 22 • 5
A Programming Paradigm for Spatiotemporal Composability Paper • 2608.25512 • Published 6 days ago • 13
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published 6 days ago • 266
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training Paper • 2608.24845 • Published 7 days ago • 15
Meta^n: Recursive Self-Improvement through Emergent Depth Paper • 2608.24735 • Published 7 days ago • 15
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback Paper • 2608.24794 • Published 7 days ago • 6
GameXpert-Bench: How Far Are Coding Agents from Expert Game Development? Paper • 2608.21833 • Published 10 days ago • 17
InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter Paper • 2608.20910 • Published 11 days ago • 38