Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Technische Universität München（慕尼黑技术大学）；Vertex Lab（Vertex实验室）；Australian National University（澳大利亚国立大学）
Hanlin Chen, Jiaxin Wei, Xibin Song, Yifu Wang, Steve Wang, Hongdong Li, Pan Ji, Gim Hee Lee
Frame-wise action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response. However, maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging. Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from \textit{Latent--RGB Cycling}, where generated latents are repeatedly decoded to RGB and re-encoded for future conditioning, and the training--inference gap induced by the \textit{error-free hypothesis}, where clean training memory fails to match prediction-corrupted inference memory. To address these challenges, we present \textbf{Robust Dreamer}, a memory-augmented framework built around how to design 3D memory and how to use it robustly. First, we introduce \textbf{Latent Gaussian Memory}, which anchors diffusion latents inherited from the generation process to Gaussian primitives and recalls them via latent-space Gaussian splatting. This provides dense, geometry-aware, view-aligned conditioning while avoiding accumulated degradation from repeated VAE conversion. Second, we propose \textbf{Deviation Learning with Dynamic Deviation Archive}, which synthesizes rollout-induced latent deviations through a one-step approximation, stores them by autoregressive stage and denoising timestamp, and injects them into historical memory during training. This exposes the generator to realistic corrupted memory states and teaches internal correction before inference. Experiments on ScanNet, DL3DV, and OmniWorldGame demonstrate state-of-the-art long-horizon performance.
Institute of Information Science, Beijing Jiaotong University（信息科学学院，北京交通大学）；Visual Intelligence +X International Cooperation Joint Laboratory of MOE（视觉智能+X国际合作联合实验室）；MT Lab, Meitu Inc（美图实验室，美图公司）；Tsinghua University（清华大学）
TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
Hangzhou Dianzi University（杭州电子科技大学）；Nanchang University（南昌大学）；School of Computer Science and Technology, Harbin Institute of Technology（计算机科学与技术学院，哈尔滨工业大学）；School of Computing and Communications, Lancaster University（计算与通信学院，兰卡斯特大学）
No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
MOE Key Laboratory of Intelligent Computing and Information Processing, Xiangtan University（湘潭大学智能计算与信息处理教育部重点实验室）；College of Information Science and Engineering, Hunan Normal University（湖南师范大学信息科学与工程学院）
Pathology-Informed Latent Diffusion Model for Anomaly Detection in Lymph Node Metastasis
School of Electrical Engineering, Korea University, Seoul 02841, Korea（韩国大学电子工程学院）；Department of Pathology, Korea University Anam Hospital and Department of Biomedical Informatics, Korea University College of Medicine, Seoul 02841, Korea（韩国大学医学院病理学系）；Department of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea（韩国天主大学医学院圣玛丽医院医院病理学系）
