4 papers
VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation
Yutong Wang, Xingtong Ge, Enhuai Liu +6
Video creation spans text-to-video (T2V), image-to-video (I2V), and condition-based generation, yet video diffusion models remain costly because they repeatedly evaluate large back…
PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers
Yutong Wang, Xingtong Ge, Enhuai Liu +4
Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction error an incomplete predictor of fin…
LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration
Enhuai Liu, Yunke Wang, Yutong Wang +2
Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and dura…
Investigating Memorization in Video Diffusion Models
Chen Chen, Enhuai Liu, Daochang Liu +2
Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially gene…