PAPER·yesterdaySol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention SparsificationHugging Face Papers
PAPER·May 28, 2026GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-PreserverarXiv
PAPER·May 27, 2026RT-Lynx: Putting GEMM Sparsity in the Right Way for Diffusion ModelsHugging Face Papers
PAPER·May 25, 2026Rethinking Cross-Layer Information Routing in Diffusion TransformersHugging Face Papers
PAPER·May 22, 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion TransformersHugging Face Papers
PAPER·May 22, 2026RiT: Vanilla Diffusion Transformers Suffice in Representation SpaceHugging Face Papers
PAPER·May 14, 2026TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D TrackingHugging Face Papers
PAPER·May 11, 2026Mean Mode Screaming: Mean-Variance Split Residuals for 1000-Layer Diffusion TransformersHugging Face Papers
PAPER·March 31, 2026On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion TransformersHugging Face Papers
PAPER·March 27, 2026Calibri: Enhancing Diffusion Transformers via Parameter-Efficient CalibrationHugging Face Papers
