Foundation Model
Foundation models are large, pre-trained AI models designed to generalize across diverse tasks and datasets, offering a powerful alternative to task-specific models. Current research emphasizes adapting these models to various domains, including healthcare (e.g., medical image analysis, EEG interpretation), scientific applications (e.g., genomics, weather forecasting), and robotics, often employing architectures like transformers and mixtures of experts with innovative gating functions. This approach promises to improve efficiency and accuracy in numerous fields by leveraging the knowledge embedded within these powerful models, streamlining data analysis and enabling new applications previously hindered by data scarcity or computational limitations.
Papers - Page 3
ExChanGeAI: An End-to-End Platform and Efficient Foundation Model for Electrocardiogram Analysis and Fine-tuning
Lucas Bickmann, Lucas Plagwitz, Antonius Büscher, Lars Eckardt, Julian VargheseUniversity Münster●University Hospital M¨unsterTraining Video Foundation Models with NVIDIA NeMo
Zeeshan Patel, Ethan He, Parth Mannan, Xiaowei Ren, Ryan Wolf, Niket Agarwal, Jacob Huffman, Zhuoyao Wang, Carl Wang, Jack Chang, Yan Bai+18NVIDIAUniReg: Foundation Model for Controllable Medical Image Registration
Zi Li, Jianpeng Zhang, Tai Ma, Tony C. W. Mok, Yan-Jie Zhou, Zeli Chen, Xianghua Ye, Le Lu, Dakai JinAlibaba Group●Zhejiang University●The First Affiliated Hospital of College of Medicine
Revisiting semi-supervised learning in the era of foundation models
Ping Zhang, Zheda Mai, Quang-Huy Nguyen, Wei-Lun ChaoThe Ohio State UniversityFoundation Models for Spatio-Temporal Data Science: A Tutorial and Survey
Yuxuan Liang, Haomin Wen, Yutong Xia, Ming Jin, Bin Yang, Flora Salim, Qingsong Wen, Shirui Pan, Gao Cong
FP3: A 3D Foundation Policy for Robotic Manipulation
Rujia Yang, Geng Chen, Chuan Wen, Yang GaoTsinghua University●Shanghai AI Laboratory●Shanghai Qi Zhi Institute●UC San DiegoReconstruct Anything Model: a lightweight foundation model for computational imaging
Matthieu Terris, Samuel Hurault, Maxime Song, Julian TachellaUniversité Paris-Saclay●Inria●CEA●ENS Paris●PSL●CNRS●CNRS UAR 851●ENSL●CNRS UMR 5672YuE: Scaling Open Foundation Models for Long-Form Music Generation
Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, Jiahao Pan, Yongyi Zang, Haohe Liu, Yiming Liang, Wenye Ma, Xingjian Du, Xinrun Du, Zhen Ye+45Proc4Gem: Foundation models for physical agency through procedural generation
Yixin Lin, Jan Humplik, Sandy H. Huang, Leonard Hasenclever, Francesco Romano, Stefano Saliceti, Daniel Zheng, Jose Enrique Chen+13Google DeepMindMetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model
Haonan Chen, Junxiao Li, Ruihai Wu, Yiwei Liu, Yiwen Hou, Zhixuan Xu, Jingxiang Guo, Chongkai Gao, Zhenyu Wei, Shensi Xu, Jiaqi Huang, Lin ShaoNational University of Singapore●NUS Guangzhou Research Translation and Innovation Institute●Nanjing University●Peking University●Shanghai...+1
TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces
Guillaume Quétant, Pavlo Molchanov, Slava VoloshynovskiyUniversity of Geneva●NVIDIASeedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
Lixue Gong, Xiaoxia Hou, Fanshi Li, Liang Li, Xiaochen Lian, Fei Liu, Liyang Liu, Wei Liu, Wei Lu, Yichun Shi, Shiqi Sun, Yu Tian, Zhi Tian, Peng Wang+14ByteDanceEndo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion
Mona Sheikh Zeinoddin, Mobarakol Islam, Zafer Tandogdu, Greg Shaw, Mathew J. Clarkson, Evangelos Mazomenos, Danail StoyanovUniversity College LondonA Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications
Siyuan Mu, Sen LinSichuan Agricultural University●University of Houston