Geometry-Aware Rotary Position Embedding for Consistent Video World Model Paper • 2602.07854 • Published Feb 8 • 10
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning Paper • 2602.13515 • Published Feb 13 • 44
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation Paper • 2602.02214 • Published Feb 2 • 24
UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers Paper • 2512.04504 • Published Dec 4, 2025 • 18
UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers Paper • 2511.20123 • Published Nov 25, 2025 • 18
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention Paper • 2509.24006 • Published Sep 28, 2025 • 119
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers Paper • 2502.15894 • Published Feb 21, 2025 • 20