Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal attention, yet its KV cache grows linearly with frames, causing memory overflow and quality degradation. We present RetrieveVGGT, a training-free framework, which formulates context construction for VGGT as a retrieval problem. By retrieving a fixed number of relevant frames at each step, VGGT maintains a controllable memory budget, which is close to its training context length. Interestingly, we find that the similarity between current frame queries and cached history frame keys at the first global attention layer of VGGT is already a strong indicator of relevance, eliminating the need for additional learned scoring. To enhance information diversity similar to a recommender system, we propose Segment Sampling so that the retrieval spans distinct relevant segments rather than a single high-similarity region. We design a pose-aware spatial memory mechanism that organizes history frames according to their already estimated camera poses, enabling location-aware retrieval. Extensive experiments demonstrate that RetrieveVGGT achieves state-of-the-art performance, outperforming StreamVGGT, TTT3R, and InfiniteVGGT while maintaining constant memory usage regardless of sequence length. Code is available at https://github.com/zzctmd/RetrieveVGGT.
Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
Nanjing University of Science and Technology（南京理工大学）；Ant Group（蚂蚁集团）；National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）
SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding
Xiamen University（厦门大学）；Beijing Institute of Technology（北京理工大学）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；University of Hong Kong（香港大学）；China Telecom（中国电信）
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
Sun Yat-sen University（中山大学）；OPPO AI Center（OPPO人工智能中心）；Shenzhen Loop Area Institute（深圳河套学院）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）
Dynamic Hub-and-Spoke Memory for Streaming Video Understanding
Northeastern University（东北大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Tulane University（杜兰大学）；University of Virginia（弗吉尼亚大学）；Adobe Research（奥多比研究院）
WAT: Online Video Understanding Needs Watching Before Thinking
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（国家人类-机器混合增强智能重点实验室，人工智能与机器人研究院，西安交通大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；University of Science and Technology Beijing（北京科技大学）
We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where performance of existing SMPL-based models are significantly affected by the distribution shift represented by different camera parameters, bone lengths, backgrounds, and occlusions. We tackle this problem through online adaptation, gradually correcting the model bias during testing. There are two main challenges: First, the lack of 3D annotations increases the training difficulty and results in 3D ambiguities. Second, non-stationary data distribution makes it difficult to strike a b…
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Lab. of Computer Network and Information Integration, Southeast University（东南大学计算机网络与信息集成重点实验室）；Zhongguancun Academy（中关村学院）；Zhongguancun Institute of Artificial Intelligence（中关村人工智能研究院）；Institute of Automation, CAS（中国科学院自动化研究所）
