Video diffusion models generate visually compelling short-term sequences but often struggle to preserve scene geometry and object structure over time. In this paper, we first demonstrate that current video attention cannot identify reliable correspondences across frames, with responses dispersed across multiple regions even after recognizable scene structure has emerged. We argue that reliable cross-frame associations are essential for information exchange as scene structure forms in video generation. Thus, we introduce Geometry Attention Distillation (GAD), which transfers correspondences from a frozen geometry model's attention to video attention. Extracted from clean videos, these correspondences link the same static surface or moving object across frames. Since structure formation begins in deeper layers at higher noise and shallower layers at lower noise, we apply attention distillation at a student layer selected according to the noise timestep. After training, video attention focuses more consistently on corresponding locations. Experiments across all three video backbones demonstrate improved long-range scene consistency and dynamic temporal consistency, with geometric gains across generation lengths. On Wan2.2 5B, GAD improves cross-frame matching accuracy by at least 30% over the Wan baseline on both long-range benchmarks. Notably, GAD achieves these gains without additional inference modules, offering a promising approach to efficient and consistent video-based world simulation. Project page: https://fantasy-amap.github.io/GAD/.
Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）；University of Sydney（悉尼大学）
Video style transfer techniques inspire many exciting applications on mobile devices. However, their efficiency and stability are still far from satisfactory. To boost the transfer stability across frames, optical flow is widely adopted, despite its high computational complexity, e.g. occupying over 97% inference time. This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm. We adopt two teacher networks, one of which takes optical flow during inference while the other does not. The output difference between these two teacher networks highlig…
Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
Tsinghua University（清华大学）；Kuaishou Technology（快手科技）；Harbin Institute of Technology (ShenZhen)（哈尔滨工业大学（深圳））；Beijing University of Posts and Telecommunications（北京邮电大学）
Streaming Autoregressive Video Generation via Diagonal Distillation
South China University of Technology（南方科技大学）；Westlake University（西湖大学）；Johns Hopkins University（约翰霍普金斯大学）；University of California, Merced（加州大学默塞德分校）；The Chinese University of Hong Kong（香港中文大学）
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）；SGIT AI Lab, State Grid Corporation of China（国家电网公司SGIT人工智能实验室）；Zhejiang University of Technology（浙江工业大学）；Baidu（百度）
VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation
University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；Hong Kong University of Science and Technology（香港科技大学）；Chinese University of Hong Kong（香港中文大学）
Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
Sun Yat-Sen University（中山大学）；ByteDance Seed Vision（字节跳动种子视觉）；Guangdong Provincial Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（教育部机器智能与高级计算重点实验室）；Pazhou Lab (HuangPu), Guangzhou, China（琶洲实验室（黄埔），广州，中国）
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
University of Wisconsin Madison（威斯康星大学麦迪逊分校）；Adobe Research（Adobe 研究院）；University of California Los Angeles（加利福尼亚大学洛杉矶分校）；University of California Davis（加利福尼亚大学戴维斯分校）
When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators
Zhejiang University of Technology（浙江工业大学）；University of New South Wales (UNSW Sydney)（新南威尔士大学（悉尼））；University of Auckland（奥克兰大学）；Zhejiang University（浙江大学）
HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models
Shanghai Jiao Tong University（上海交通大学）；S-Lab, Nanyang Technological University（新加坡南洋理工大学S-Lab实验室）；University of Science and Technology of China（中国科学技术大学）；Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Adobe Research（奥多比研究院）；The Chinese University of Hong Kong（香港中文大学）；CPII under InnoHK（InnoHK下属CPII机构）
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
Generative Video Compression with Adaptive Score Distillation
Communication University of China（中国传媒大学）；University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
This paper investigates a novel task of talking face video generation solely from speeches. The speech-to-video generation technique can spark interesting applications in entertainment, customer service, and human-computer-interaction industries. Indeed, the timbre, accent and speed in speeches could contain rich information relevant to speakers' appearance. The challenge mainly lies in disentangling the distinct visual attributes from audio signals. In this article, we propose a light-weight, cross-modal distillation method to extract disentangled emotional and identity information from unlab…
