Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models
School of Biomedical Engineering, Tsinghua University, Beijing, China（生物医学工程学院，清华大学，北京，中国）；Tsinghua Laboratory of Brain and Intelligence, Tsinghua University, Beijing, China（脑与智能实验室，清华大学，北京，中国）；School of Basic Medical Sciences, Tsinghua University, Beijing, China（基础医学学院，清华大学，北京，中国）；Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China（心理学与认知科学系，清华大学，北京，中国）
Yixuan Liu, Zhiyuan Ma, Likai Tang, Runmin Gan, Xinche Zhang, Jinhao Li, Chao Xie, Sen Song
发表信息：
Proceedings of the Annual Meeting of the Cognitive Science Society, 48 (2026), 167-174
How large language models (LLMs) align with the neural representation and computation of human language is a central question in cognitive science. Using representational geometry as a mechanistic lens, we addressed this by tracking entropy, curvature, and fMRI encoding scores throughout Pythia (70M-1B) training. We identified a geometric modularization where layers self-organize into stable low- and high-complexity clusters. The low-complexity module, characterized by reduced entropy and curvature, consistently better predicted human language network activity. This alignment followed heterogeneous spatial-temporal trajectories: rapid and stable in temporal regions (AntTemp, PostTemp), but delayed and dynamic in frontal areas (IFG, IFGorb). Crucially, reduced curvature remained a robust predictor of model-brain alignment even after controlling for training progress, an effect that strengthened with model scale. These results links training-driven geometric reorganization to temporal-frontal functional specialization, suggesting that representational smoothing facilitates neural-like linguistic processing.
Beyond representational alignment with brain-guided language models for robust reasoning
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University（北京大学通用人工智能国家重点实验室、智能科学与技术学院）；Department of Psychological and Cognitive Sciences, Tsinghua University（清华大学心理与认知科学系）；Microsoft Research Asia（微软亚洲研究院）
Linguistics and Human Brain: A Perspective of Computational Neuroscience
Institute of AI and Robotics, College of Intelligent Robotics and Advanced Manufacturing, Fudan University（人工智能与机器人研究院，智能机器人与先进制造学院，复旦大学）；Department of Language Science and Technology, The Hong Kong Polytechnic University（语言科学与技术系，香港理工大学）；Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）
Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabase
Faculty of Psychology, University of Basel（巴塞尔大学心理学系）；Center for Adaptive Rationality, Max Planck Institute for Human Development（马克斯·普朗克人类发展研究所适应性理性中心）；School of Psychology, UNSW（新南威尔士大学心理学学院）
Large Language Models Align with the Human Brain during Creative Thinking
EPFL（瑞士联邦理工学院洛桑）；Università della Svizzera italiana (USI)（意大利语区大学（瑞士））；Wesleyan University（卫斯理大学）；Paris Brain Institute (ICM)（巴黎大脑研究所）；Pennsylvania State University（宾夕法尼亚州立大学）
Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures
MOE Key Lab of Computational Linguistics, Peking University（计算语言学MOE实验室，北京大学）；Beijing Academy of Artificial Intelligence, Beijing, China（北京人工智能研究院，北京，中国）；Nanjing University of Science and Technology（南京理工大学）；Purdue University（普渡大学）
Do Large Language Models Mirror Cognitive Language Processing?
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；College of Computer and Information Engineering, Tianjin Normal University（天津师范大学计算机与信息工程学院）
Achieving More Human Brain-Like Vision via Human EEG Representational Alignment
Department of Psychology, The Ohio State University（心理学系，俄亥俄州立大学）；McGovern Institute for Brain Research, Massachusetts Institute of Technology（脑科学研究所，麻省理工学院）；Department of Neuroscience, The University of Texas at Dallas（神经科学系，德克萨斯大学达拉斯分校）
Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
Peking University（北京大学）；Zhejiang University（浙江大学）；Beijing Language and Culture University（北京语言大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
Flexibility and Invariance of Object Representations in the Human Brain
Neuroscience Institute, Carnegie Mellon University（卡内基梅隆大学神经科学研究所）；Department of Psychology, Carnegie Mellon University（卡内基梅隆大学心理学系）；Department of Machine Learning, Carnegie Mellon University（卡内基梅隆大学机器学习系）；Department of Neurosurgery, University of Rochester Medical Center（罗切斯特大学医学中心神经外科）
Shared representations in brains and models reveal a two-route cortical organization during scene perception
Department of Cognition, Development and Education Psychology, Faculty of Psychology, University of Barcelona（认知、发展与教育心理学系，心理学学院，巴塞罗那大学）；Institute of Neurosciences, University of Barcelona（神经科学研究所，巴塞罗那大学）；Bellvitge Institute for Biomedical Research（Bellvitge生物医学研究 institute）
Groningen Institute for Evolutionary Life Sciences, University of Groningen（格罗宁根进化生命科学研究所，格罗宁根大学）；Bernoulli Institute, University of Groningen（伯努利研究所，格罗宁根大学）
Net2Brain: A Toolbox to compare artificial vision models with human brain responses
Department of Computer Science, Goethe Universität（冯·迪斯大学计算机科学系）；Department of Education and Psychology, Freie Universität Berlin（柏林自由大学教育与心理学系）；Berlin School of Mind and Brain, Faculty of Philosophy（柏林心灵与大脑学校，哲学学院）；Bernstein Center for Computational Neuroscience Berlin（柏林计算神经科学中心）
Hong Kong Baptist University（香港浸会大学）；Institute of Computational and Theoretical Studies, Hong Kong Baptist University（香港浸会大学计算与理论研究所）；Sun Yat-sen University（中山大学）；City University of Hong Kong（香港城市大学）
Recurrence is required to capture the representational dynamics of the human visual system
MRC Cognition and Brain Sciences Unit, University of Cambridge（英国医学研究委员会认知与脑科学单元，剑桥大学）；Radboud University（拉德堡德大学）；Donders Institute for Brain, Cognition and Behaviour（邓德斯脑、认知与行为研究所）；University of Amsterdam（阿姆斯特丹大学）；Freie Universität Berlin（柏林自由大学）；Columbia University（哥伦比亚大学）
The Neural Representation Benchmark and its Evaluation on Brain and Machine
McGovern Institute for Brain Research（麦戈文脑科学研究所）；Massachusetts Institute of Technology（麻省理工学院）
开发有效学习表征的一个关键要求是对它们进行评估，并与我们已知的有效表征进行比较。在自然的感官领域，社区将大脑视为灵感的来源和成功的隐含基准。然而，还不可能直接针对神经系统中包含的表示来直接测试表征学习算法。在这里，我们提出了一个新的视觉表征基准，在此基础上，我们直接测试了猕猴多个视觉皮层区域的神经表征（利用来自[Majaj等人，2012]），并且可以在其上测试产生特征空间的任何计算机视觉算法。基准测试通过计算核矩阵的有序特征分解的分类损失来测量神经或机器表示的有效性[Montavon等人，2011年]。在我们的分析中，我们发现，视觉区IT的神经表征优于视觉区V4。在我们对代表性学习算法的分析中，我们发现三层模型接近V4的代表性性能和[Le et al.，2012]超越了V4的性能。令人印象深刻的是，我们发现最近的监督算法[Krizhevsky等人，2012]实现了与IT的性能相当的中等水平的图像变化难度，并超过IT在更高的难度水平。我们相信这个结果代表了一个重要的里程碑：它是我们发现的第一个超过我们目前对IT表示性能的估计的学习算法。我们希望这个基准将有助于社区匹配视觉皮层的表征性能，并将作为大脑和机器中衍生的表征之间进一步对应的初始集合点。
Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments
Zuckerman Mind Brain Behavior Institute（祖克曼心智脑行为研究所）；Columbia University（哥伦比亚大学）
Targeted perturbations reveal brain-like local coding axes in robustified, but not standard, ANN-based brain models
Center for Excellence in Computational Cognition, Georgia Tech（计算认知卓越中心，佐治亚理工学院）；School of Mathematics, Georgia Tech（数学学院，佐治亚理工学院）；School of Psychology, Georgia Tech（心理学学院，佐治亚理工学院）
研究用小规模对抗探针检验基于 ANN 的视觉脑模型，发现鲁棒模型具有更稳定、可泛化且类脑的局部编码轴，可作为超越预测准确率的模型评估判据。
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
Department of Cognition, Development and Education Psychology, University of Barcelona（巴塞罗那大学认知、发展与教育心理学系）；Institute of Neurosciences, University of Barcelona（巴塞罗那大学神经科学研究所）；Department of Computer Science, Cornell University（康奈尔大学计算机科学系）；Bellvitge Institute for Biomedical Research, Spain（西班牙贝尔维德生物医学研究 institute）
A specialized face-processing network consistent with the representational geometry of monkey face patches
School of Cognitive Sciences (SCS), Institute for Research on Fundamental Sciences (IPM)（基础科学研究所（IPM）认知科学学院）；Monash University（莫纳什大学）；Shahid Rajaee Teacher Training University（沙希德·拉贾伊师范大学）；Massachusetts Institute of Technology（麻省理工学院）
Dissociable neural representations of adversarially perturbed images in convolutional neural networks and the human brain
National Digital Switching System Engineering and Technological Research Center（国家数字交换系统工程技术研究中心）；People's Hospital of Henan Province（河南省人民医院）；Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属精神卫生中心）；Institute of Psychology and Behavioral Science, Shanghai Jiao Tong University（上海交通大学心理与行为科学研究院）
