Latent Space Alignment

Ask about this topic

Overview

Latent space alignment studies how to make representations from different models, modalities, domains, or people comparable and useful together. Common approaches learn linear or orthogonal maps with Procrustes methods, use optimal transport or shared semantic anchors, or regularize representations to preserve geometry and task-relevant structure. These methods support tasks such as model stitching, cross-modal retrieval, domain adaptation, and cross-subject brain decoding, evaluated through measures including retrieval accuracy, activation reconstruction, and downstream task performance. A central tension is that geometric or distributional similarity does not guarantee functional compatibility: alignment can preserve nuisance information, depend on paired examples, or improve a similarity metric without improving the task.

Latest papers

CardsList

76 papers20 papers in the last four weeks, up 122% on the four weeks before. 0.1% of all new papers.

  1. More Data Cannot Break a Symmetry: Identifiability by Design

    Aug 27, 2026Jing Xu, Christopher KananRepresentation IdentifiabilityParameter Identifiability

    Department of Computer Science, University of Rochester

  2. HALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognition

    Aug 27, 2026Zihan Ding, Liyu Zhang, Xiaomin OuyangHuman Activity RecognitionMultimodal Foundation Models

    Hong Kong University of Science and Technology Hong Kong, China

  3. SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval

    Aug 19, 2026Zhenyao Cui, Siyuan Kan, Siyang Li +2Cross-Subject EEG DecodingEEG-Based Visual Decoding

    School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China

  4. Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence

    Aug 17, 2026Jiaqi Wang, Huawen Hu, Shu ZhangNeural DecodingLatent Space Alignment

    School of Computer Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China

  5. The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning

    Aug 17, 2026Małgorzata Łazęcka, Ewa SzczurekDisentangled Representation LearningLatent Space Alignment

    Faculty of Mathematics, Informatics, and Mechanics, University of Warsaw Warsaw, Poland · Institute of AI for Health, Helmholtz Munich Munich, Germany

  6. Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction

    Aug 16, 2026Fan Yang, Youngsun Wi, Jinhao Yu +2Sim-to-Real TransferTactile Sensing for Robotic Manipulation

    F. Yang, J. Yu, N. Fazeli, and D. Berenson are with the University of Michigan, Ann Arbor, MI, USA. · Y. Wi is with Google DeepMind. This work was initiated prior to and conducted independently of Google DeepMind.

  7. How Far Do Simple Transformations Translate Across Text Embedding Models?

    Aug 6, 2026Sid Ali Hamideche, Louis-Adrien Dufrène, Quentin Lampin +1Representation LearningText Embedding Evaluation

    Orange Research · Orange

  8. Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

    Jun 30, 2026Anh Nguyen, Ngan Nguyen, Duc Vu +11Diffusion Model DistillationCross-Architecture Knowledge Distillation

    Qualcomm AI Research† · University of Wisconsin–Madison · Johns Hopkins University +1

  9. Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

    Jun 23, 2026Wangyi Pu, Michele ScarpinitiFlow MatchingSpeech Enhancement

    Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Italy

  10. Subspace-Constrained Federated Learning with Low-Rank Adaptation

    Jun 21, 2026Neranjan Senarath, Rohit Muralitharan, Sadia AsifFederated Learning AggregationNon-IID Federated Learning

    Department of ECSE Rensselaer Polytechnic Institute Troy, NY 12180, USA · Department of Computer Science Rensselaer Polytechnic Institute Troy, NY 12180, USA

  11. PACT: Preserving Anchored Cores in Task-vectors for Model Merging

    Jun 17, 2026Ningyuan Shi, Zhipeng Zhou, Hao Wang +2Multi-Task LearningTask Vector Merging

    Shanghai Jiao Tong University · Nanyang Technological University · The Hong Kong University of Science and Technology (Guangzhou)

  12. Learning aligned EEG representations with subject-specific encoders

    Jun 15, 2026Bruna J. Lopes, Gabriel Schwartz, Sylvain Chevallier +2Cross-Subject EEG DecodingMI Classification

    University of São Paulo, São Paulo, Brazil · Université Paris-Saclay, Inria TAU team, LISN-CNRS, France · Institut de neuromodulation, GHU Paris, psychiatrie et neurosciences, centre hospitalier Sainte-Anne, pôle hospitalo-universitaire 15, Université Paris Cité, Paris, France +3

  13. Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE

    Jun 14, 2026Angeliki Papathanasiou, Jascha Achterberg, Thomas E. Nichols +1Variational AutoencodersNeural Decoding

    Centre for Neural Circuits and Behaviour, Department of Physiology Anatomy and Genetics, University of Oxford · Big Data Institute, Nuffield Department of Medicine, University of Oxford

  14. Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

    Jun 4, 2026XiuYu Zhang, Junfeng Fang, Zhenkai LiangVLM EvaluationLatent Visual Reasoning

    National University of Singapore

  15. Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks

    May 26, 2026Ali Hussaini Umar, Alessandro LaioNeural Representation GeometryLatent Space Alignment

    SISSA · SISSA & ICTP

  16. Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m

    May 23, 2026Jordan F. McCannOrthogonal Procrustes AlignmentTransformer Interpretability

    Independent Researcher

  17. LatentUMM: Dual Latent Alignment for Unified Multimodal Models

    May 18, 2026Yinyi Luo, Wenwen Wang, Hayes Bai +2Cross-Modal LearningUnified Multimodal Models

    Carnegie Mellon University · William & Mary

  18. SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations

    May 10, 2026Mario Edoardo Pandolfo, Enrico Grimaldi, Lorenzo Marinucci +4Neural Representation GeometryVisual Representation Learning

    Dept. Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy. · National Inter-University Consortium for Telecommunications (CNIT), Parma, Italy. · Dept. of Statistical Sciences, Sapienza University of Rome, Rome, Italy. +1

  19. Seeing the imagined: latent functional alignment in visual imagery decoding from fMRI data

    Apr 15, 2026Fabrizio Spera, Tommaso Boccato, Michal Olak +2Neural DecodingVisual Neuroscience

    Department of Biomedicine and Prevention, University of Rome Tor Vergata, Rome, Italy · Tether Evo · A.A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA

  20. Compatibility of Face Embeddings Across Deep Neural Networks

    Apr 8, 2026Fizza Rubab, Yiying Tong, Arun RossFace RecognitionLatent Space Alignment

    Michigan State University

  21. Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation

    Apr 4, 2026Zhifu Wei, Yizhou Dang, Guibing Guo +2Recommender SystemsSequential Recommendation

    Northeastern University, Shenyang, China · Tianjin University, Tianjin, China · Singapore University of Technology and Design, Singapore, Singapore

  22. Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval

    Apr 3, 2026Seiji Maekawa, Moin Aminnaseri, Pouya Pezeshkpour +1Dense RetrievalTransfer Learning

    Megagon Labs

  23. Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models

    Mar 24, 2026Aueaphum Aueawatthanaphisut, Kuepon AuewattanapisutPAC-Bayesian TheoryDomain Adaptation

    School of Information, Computer, and Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathumthani, Thailand · epartment of Architecture, Faculty of Architecture Khon Kaen University Khon Kaen, Thailand

  24. The Universal Normal Embedding

    Mar 23, 2026Chen Tasker, Roy Betser, Eyal Gofer +2Latent Space AlignmentVisual Representation Learning

    Viterbi Faculty of Electrical and Computer Engineering Technion - Israel Institute of Technology

  25. Statistical Learning for Latent Embedding Alignment with Application to Brain Encoding and Decoding

    Mar 22, 2026Shuoxun Xu, Zhanhao Yan, Lexin LiLatent Space AlignmentNeural Decoding

    University of California at Berkeley

  26. IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment

    Mar 20, 2026Simone Magistri, Dipam Goswami, Marco Mistretta +3Latent Space AlignmentModality Gap in VLMs

    Media Integration and Communication Center (MICC), University of Florence, Italy · Department of Computer Science, Universitat Aut`onoma de Barcelona, Spain · Computer Vision Center, Barcelona, Spain +1

  27. Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

    Mar 19, 2026Matt Gorbett, Suman JanaLatent Space AlignmentLLM Alignment

    Capital One New York, NY 10003, USA · Department of Computer Science Columbia University New York, NY 10027, USA

  28. Manifold-Matching Autoencoders

    Mar 17, 2026Laurent Cheret, Vincent Létourneau, Isar Nejadgholi +3Multidimensional ScalingAutoencoders

    Department of Computer Science, University of Ottawa, Ottawa, Canada · MILA, Montréal, Canada · National Research Council of Canada, Ottawa, Canada

  29. Distilling Latent Manifolds: Resolution Extrapolation by Variational Autoencoders

    Mar 15, 2026Jiaming Chu, Tao Wang, Lei JinPosition ExtrapolationVariational Autoencoders

    School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China

  30. Predictive Spectral Calibration for Source-Free Test-Time Regression

    Mar 10, 2026Nguyen Viet Tuan Kiet, Huynh Thanh Trung, Pham Huy HieuTest-Time AdaptationSource-Free Domain Adaptation

    Hanoi University of Science and Technology · VinUniversity