Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models Paper • 2605.09681 • Published May 10 • 10
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation Paper • 2605.15141 • Published May 14 • 96
Exploring Spatial Intelligence from a Generative Perspective Paper • 2604.20570 • Published Apr 22 • 23
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details Paper • 2604.06870 • Published Apr 8 • 44
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models Paper • 2602.09713 • Published Feb 10 • 8
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality Paper • 2512.07951 • Published Dec 8, 2025 • 51
