6 accepted papers
To achieve real-time video generation, current approaches distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models. This process involves an *architectural gap*, as it converts full attention into causal attention. In this paper, we demonstrate that existing m…
In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. Interestingly, we find that attention weights can be decoupled into two matrices: a small fraction of large weights with hig…
Despite advances, video diffusion transformers still struggle to generalize beyond their training length, a challenge we term video length extrapolation. We identify two failure modes: model-specific periodic content repetition and a universal quality degradation. Prior works attempt to solve repeti…
Preliminary progress has been made in using deep learning networks for tooth segmentation and numbering, as well as pathological identification in dental panoramic images. However, The publicly available datasets specifically for children’s teeth are very scarce. To address this issue, this paper pr…
Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos. However, generating even longer videos with temporal coherence remains a major challenge and existing length extrapolation methods lead to temporal repetition or motion deceleration. In this w…
Diffusion models have obtained substantial progress in image-to-video generation. However, in this paper, we find that these models tend to generate videos with less motion than expected. We attribute this to the issue called conditional image leakage, where the image-to-video diffusion models (I2V-…