We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability. Our framework efficiently compresses multiple image observations into the fast weights of the TTT layer, forming an implicit 3D representation in the latent space that can be decoded into various explicit formats, such as Gaussian Splats (GS) for downstream applications. The online learning variant of our model supports progressive 3D reconstruction and refinement from streaming observations. We demonstrate that pretraining on novel view synthesis tasks effectively transfers to explicit 3D modeling, resulting in improved reconstruction quality and faster convergence. Extensive experiments show that our method achieves superior performance in feedforward 3D Gaussian reconstruction compared to state-of-the-art approaches on both objects and scenes.
Autoregressive B-Rep Shape Generation with Parametric Surfaces
The University of Hong Kong(香港大学);Deemos Technology Co., Ltd.(迪莫斯科技有限公司);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);ShanghaiTech University(上海科技大学);Texas A&M University(德克萨斯A&M大学)
Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
Beihang University(北航大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Wuhan University(武汉大学);The Chinese University of Hong Kong(香港中文大学);Tsinghua University(清华大学)
Physics-Driven Autoregressive State Space Models for Medical Image Reconstruction
Dept. of Electrical and Electronics Engineering, and National Magnetic Resonance Research Center (UMRAM), Bilkent University(电气与电子工程系,国家磁共振研究中心(UMRAM),比尔肯大学)
Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction
The Chinese University of Hong Kong(香港中文大学);The Hong Kong Polytechnic University(香港理工大学);The University of New South Wales(新南威尔士大学);Southeast University(东南大学)
MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations
Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University(福建省城市智能感知与计算重点实验室,厦门大学);Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics, Xiamen University(多媒体可信感知与高效计算教育部重点实验室,厦门大学信息学院);National Institute for Data Science in Health and Medicine, Xiamen University(厦门大学健康医疗大数据国家研究院);ShanghaiTech University(上海科技大学)
An Efficient Implicit Neural Representation Image Codec Based on Mixed Autoregressive Model for Low-Complexity Decoding
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Peng Chen Laboratory(鹏城实验室);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Huawei Technology(华为技术有限公司)
UniT: Unified Geometry Learning with Group Autoregressive Transformer
Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (GZ), Guangzhou, P.R.China(香港理工大学(广州)系统中心智能交通研究组,中国广东省广州市);The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, P.R.China(人机混合增强智能国家级重点实验室,西安交通大学,中国陕西省西安市);Applied Science, Amazon.com, Inc., USA(亚马逊公司应用科学部,美国)
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Huazhong University of Science and Technology(华中科技大学);Zhongguancun Academy(中关村学院);DeepCybo;Harbin Institute of Technology(哈尔滨工业大学);Beihang University(北京航空航天大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Zhengzhou University(郑州大学);Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院)
MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Tsinghua University(清华大学);Peking University(北京大学);Microsoft(微软公司)
Spatiotemporal Satellite Image Downscaling with Transfer Encoders and Autoregressive Generative Models
University of Toronto(多伦多大学);Harvard T.H. Chan School of Public Health(哈佛大学T.H. Chan公共卫生学院);Harvard Medical School(哈佛医学院);VA Healthcare System Boston, U.S. Department of Veterans Affairs(美国退伍军人事务部波士顿医疗系统)