SLA2: Sparse-Linear Attention with Learnable Routing and QAT Paper • 2602.12675 • Published 22 days ago • 53
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation Paper • 2602.02214 • Published Feb 2 • 24
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models Paper • 2601.15165 • Published Jan 21 • 72
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published Dec 18, 2025 • 95