Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation Paper • 2609.38748 • Published 5 days ago • 53
CARE: Certifying Acceleration for Vision-Language-Action Inference Paper • 2610.08917 • Published 7 days ago • 7
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness Paper • 2610.08621 • Published 7 days ago • 93
Dream4ACT: A Shared Visual Action Interface for Multi-Embodiment Video-Action Modeling Paper • 2609.40153 • Published 13 days ago • 14
E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models Paper • 2609.37533 • Published 14 days ago • 67
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing Paper • 2609.08936 • Published Sep 8 • 161