Jag: Direct Box Prediction for Efficient Visual Grounding Paper • 2610.13239 • Published 8 days ago • 6
A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning Paper • 2606.03335 • Published 11 days ago • 29
Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training Paper • 2610.05416 • Published 13 days ago • 21
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation Paper • 2610.00686 • Published 17 days ago • 12
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention Paper • 2609.15810 • Published Sep 14 • 51
Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper • 2608.16590 • Published Aug 17 • 154
Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation Paper • 2608.13391 • Published Aug 13 • 20