Mapping behavioral actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioral data increases, there is growing interest in modeling neural dynamics during adaptive behaviors to probe neural representations. In particular, neural latent embeddings can reveal underlying correlates of behavior, yet, we lack non-linear techniques that can explicitly and flexibly leverage joint behavior and neural data. Here, we fill this gap with a novel method, CEBRA, that jointly uses behavioral and neural data in a hypothesis- or discovery-driven manner to produce consistent, high-performance latent spaces. We validate its accuracy and demonstrate our tool's utility for both calcium and electrophysiology datasets, across sensory and motor tasks, and in simple or complex behaviors across species. It allows for single and multi-session datasets to be leveraged for hypothesis testing or can be used label-free. Lastly, we show that CEBRA can be used for the mapping of space, uncovering complex kinematic features, and rapid, high-accuracy decoding of natural movies from visual cortex.
Are LLM Agents Behaviorally Coherent? A Latent Profiling Approach for Social Simulation
Department of Computer Science and Engineering, University of Minnesota(明尼苏达大学计算机科学与工程系);Department of African American & African Studies, University of Minnesota(明尼苏达大学非裔美国人与非洲研究系);Department of Sociology, University of Chicago(芝加哥大学社会学系)
Learnable Residual-Based Latent Denoising in Semantic Communication
Department of Electronic Engineering, Shanghai Jiao Tong University(电子工程系,上海交通大学);School of Cyber and Engineering, Shanghai Jiao Tong University(网络与工程学院,上海交通大学);Department of Electrical and Computer Engineering, University of Delaware(电气与计算机工程系,德雷塞尔大学);State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(网络与交换技术国家重点实验室,北京邮电大学)
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Department of Data Science & AI, Monash University(墨尔本大学数据科学与人工智能系);Faculty of Medicine Dentistry and Health Sciences, University of Melbourne(墨尔本大学医学牙科与健康科学学院);Department of Computer Science, University College London(伦敦大学学院计算机科学系)
Different representation learning objectives recover distinct latent structures from the same psychometric data
Yale University(耶鲁大学);Yale School of Public Health(耶鲁公共卫生学院);VA Connecticut Healthcare System(VA康涅狄格医疗系统);Cooperative Studies Program Coordinating Center(合作研究项目协调中心);Center for the Advancement of Research & Development in Educational Technology (CARDET)(教育技术研究与发展促进中心(CARDET))
Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data
Fordham University(福特汉姆大学);Georgia Institute of Technology(佐治亚理工学院);Icahn School of Medicine at Mount Sinai(Mount Sinai医学院);University of California, San Diego(加州大学圣地亚哥分校)
Diffusion-Based Generation of Neural Activity from Disentangled Latent Codes
Center for Machine Learning, Georgia Tech(佐治亚理工学院机器学习中心);Department of Biomedical Engineering, Georgia Tech and Emory University(佐治亚理工学院与埃默里大学生物医学工程系);AE Studio(AE工作室);Department of Neurosurgery, Emory University School of Medicine(埃默里大学医学院神经外科)
Reward-Mixing MDPs with a Few Latent Contexts are Learnable
Wisconsin Institute for Discovery, UW-Madison(威斯康星大学麦迪逊分校威斯康星发现研究所);Meta;University of Texas at Austin(德克萨斯大学奥斯汀分校);Technion(以色列理工学院);NVIDIA(英伟达(NVIDIA))
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
Department of Computing Science, University of Alberta, Canada(阿尔伯塔大学计算机科学系);Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所);Canada CIFAR AI Chair(加拿大CIFAR人工智能 chair);The University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Massachusetts Amherst(马萨诸塞大学阿姆赫斯特分校)
Separators Make Carry Propagation Learnable:The Geometry of Latent Carry in a Multiplication Transformer
Sorbonne Center for Artificial Intelligence(索邦人工智能中心);Sorbonne Université(索邦大学);Laboratoire de Probabilités, Statistique et Modélisation(概率、统计与建模实验室);CNRS(法国国家科学研究中心);Inria Paris(法国国家信息与自动化研究所巴黎分部)
Generative Modeling of Neural Dynamics via Latent Stochastic Differential Equations
Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University(机器学习与神经计算系,脑认知与行为研究所,拉德堡德大学)
Learning signatures of decision making from many individuals playing the same game
Georgia Institute of Technology(佐治亚理工学院);University of Minnesota(明尼苏达大学);Universite de Montreal(蒙特利尔大学);University of Minnesota School of Medicine(明尼苏达大学医学院)
Learnable Commutative Monoids for Graph Neural Networks
University of Cambridge(剑桥大学);DeepMind(深度思维)
图神经网络(GNN)已被证明是高度敏感的聚合函数的选择。虽然对节点的邻居求和可以近似于离散输入上的任何置换不变函数,但Cohen-Karlik et al. [2020]证明了存在集合聚合问题,其中求和不能推广到无界输入,提出了对置换不变正则化的递归神经网络作为更具表达力的聚合器。我们证明了这些结果可以推广到图域:在合成基准测试和现实问题上,配备了递归聚合器的GNN与最先进的置换不变聚合器相比具有竞争力。然而,尽管经常性聚合器的好处,其$O(V)$深度使他们既难以并行化和更难训练大型图。受GNN的行为良好的聚合器是其潜在空间上的交换幺半群的观察的启发,我们提出了一个框架,用于构建可学习的,可交换的,关联的二元运算符。有了这个,我们构建了一个聚合器的$O(\log V)$深度,并行性和依赖长度产生指数级的改善,同时实现与经常性聚合器的性能竞争。根据我们的经验观察,我们提出的可学习的交换幺半群(LCM)聚合器是一个有利的权衡高效和表达聚合器。
Stable Neural Decoding Across Sessions via Task-Conditioned Latent Alignment for Brain-Machine Interfaces
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Pittsburgh(匹兹堡大学);Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
Inria(法国国家信息与自动化技术研究院);PSL Research University(巴黎社会科学高等研究院);CMAP(巴黎高等理工学院应用数学与计算科学实验室);Ecole Polytechnique Palaiseau, France(法国巴黎高等理工学院Palaiseau分校);Sakana AI Tokyo, Japan(日本东京Sakana AI公司)