UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
Brown University（布朗大学）；Massachusetts Institute of Technology（麻省理工学院）；Meta Reality Lab（Meta现实实验室）；Max-Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所）；University of Hong Kong（香港大学）
Xiaoyan Cong, Zekun Li, Zhiyang Dou, Hongyu Li, Omid Taheri, Chuan Guo, Abhay Mittal, Sizhe An, Taku Komura, Wojciech Matusik, Michael J. Black, Srinath Sridhar
Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream tasks remains largely unclear. Prior work typically adapts pretrained generative priors to individual downstream tasks in a task-specific manner. In contrast, our goal is to unlock such priors to support a broad spectrum of downstream motion generation tasks within a single unified framework. To bridge this gap, we present UMO, a simple yet general unified formulation that casts diverse downstream tasks into compositions of atomic per-frame operations, enabling in-context adaptation to unlock the generative priors of pretrained DiT-based motion LFMs. Specifically, UMO introduces three learnable frame-level meta-operation embeddings to specify per-frame intent and employs lightweight temporal fusion to inject in-context cues into the pretrained backbone, with negligible runtime overhead compared to the base model. With this design, UMO finetunes the pretrained model, originally limited to text-to-motion generation, to support diverse previously unsupported tasks, including temporal inpainting, text-guided motion editing, text-serialized geometric constraints, and multi-identity reaction generation. Experiments demonstrate that UMO consistently outperforms task-specific and training-free baselines across a wide range of benchmarks, despite using a single unified model. Code and model will be publicly available. Project Page: https://oliver-cong02.github.io/UMO.github.io/
Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model
Beihang University（北京航空航天大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shen Yuan Honors College of Beihang University（北京航空航天大学沈元荣誉学院）；National University of Singapore（新加坡国立大学）
Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
City University of Hong Kong（香港城市大学）；The Chinese University of Hong Kong（香港中文大学）；Huawei Research（华为研究）；Great Bay University（大湾大学）；AI Technology Center, Tencent PCG（腾讯AI技术中心）；Lingnan University（岭南大学）；Hong Kong Centre for Cerebro-Cardiovascular Health Engineering（香港脑心血管健康工程中心）
A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Pengcheng Lab（鹏城实验室）；Tsinghua University（清华大学）；Harbin Medical University Cancer Hospital（哈尔滨医科大学附属肿瘤医院）；Tongji University（同济大学）
Unlocking Pretrained Vision Transformers for Time Series Classification
Helmholtz Munich（海德堡-慕尼黑研究所）；Technical University of Munich（慕尼黑技术大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；MDSI（慕尼黑数据科学研究所）；Paris Noah’s Ark Lab（巴黎诺亚实验室）
Adaptive Multi-Scale Integration Unlocks Robust Cell Annotation in Histopathology Images
Department of Computer and Information Science, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学）；Department of Bioengineering, University of Pennsylvania（生物工程系，宾夕法尼亚大学）；Department of Pathology and Laboratory Medicine, University of Pennsylvania（病理学与实验室医学系，宾夕法尼亚大学）；Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania（生物统计学、流行病学与信息学系，宾夕法尼亚大学）
Towards a Unified Copernicus Foundation Model for Earth Vision
Technical University of Munich（慕尼黑技术大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；National Technical University of Athens & National Observatory of Athens（雅典国家技术大学及雅典国家天文台）；Harokopio University of Athens（雅典哈罗科波斯大学）；NVIDIA（NVIDIA公司）
Rethinking the Adaptation of Vision Foundation Models for Efficient Cell Segmentation
School of Computer Science, University of Nottingham, UK（英国诺丁汉大学计算机科学学院）；School of Computer Science, University of Nottingham Ningbo China, China（中国宁波诺丁汉大学计算机科学学院）；School of Engineering and Physical Science, University of Lincoln, UK（英国林肯大学工程与物理科学学院）；Department of Computer Science, University of Rochester, USA（美国罗切斯特大学计算机科学系）
