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

89 papers11 papers in the last four weeks, down 48% on the four weeks before. 0.1% of all new papers.

  1. GALA: Gallery-Level Alignment for Real-Life Vision Decoding from EEG

    Nov 18, 2026Philippe Forest, Giulia Lioi, Mai Pham Quyen +3EEG-Based Visual DecodingCross-Subject EEG Decoding

  2. JEPA for astronomy: multi-survey spectral alignment puts stellar parameters on the leading principal axes

    Nov 17, 2026Xiaosheng Zhao, Rosemary F. G. Wyse, Yuan-Sen Ting +1Latent Space AlignmentJoint-Embedding Predictive Architecture

  3. Sample-Aligned Decoders for Latent Generative Models

    Nov 17, 2026Yu Lei, Yi Li, Hongcheng Gao +4Latent Space Alignment

  4. Emergent Steering Beyond Endpoint Alignment in Chemical Reaction Models

    Nov 16, 2026Yili Shen, Kehan Guo, Haomin Zhuang +1Chemical Reaction PredictionRetrosynthesis

  5. Learning a Task-Adaptive Low-Dimensional Semantic Space for Improved Visual Classification

    Nov 16, 2026Nikalal Kaldera, Wanqing Li, Chris Bunn +1Semantic Representation LearningLatent Space Alignment

  6. Over-the-Air Semantic Alignment via Dual Stacked Intelligent Metasurfaces

    Nov 14, 2026Mario Edoardo Pandolfo, Kyriakos Stylianopoulos, George C. Alexandropoulos +1Semantic CommunicationLatent Space Alignment

  7. Identifiable alignment of unpaired representations

    Nov 8, 2026Stas Syrota, Albert Lopez I Serrano, Johanne Franck +1single-cell representation learningRepresentation Alignment

  8. UniLatent: Cross-Embodiment Transfer via Latent Observation Alignment

    Nov 6, 2026Yufei Ding, Yi Du, Weiduo Yuan +5Cross-Embodiment TransferLatent Space Alignment

  9. When Are Two SAE Latents the Same Feature?

    Nov 3, 2026Alexandra Suvorikova, Ilgam Latypov, Anton Trukhan +1Sparse AutoencodersLatent Space Alignment

  10. QFacePlacement: From Arbitrary Tensorization to Semantic Spatial Correspondence in Modern Face Verification

    Nov 2, 2026Krishna Bhatia, Kavita Choudhary, Pruthwik Mishra +1Face RecognitionTensor Networks

  11. Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI

    Oct 29, 2026Serwan Jassim, Victoria Bosch, Daniel Anthes +2fMRI Representation LearningfMRI-Based Visual Decoding

  12. Five Architectures, One Shared Space Cross-Model Representational Alignment Without Weight Merging

    Oct 24, 2026Oladimeji Anthonio, Dimeji Olawuyi, Oloruntoba Ajayi +1Latent Space AlignmentRepresentation Geometry in Language Models

  13. The Geometry of Meaning in Neural Manifolds

    Oct 22, 2026Valentino MaiorcaNeural Representation GeometrySemantic Correspondence

  14. MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning

    Oct 20, 2026Kohei Yamamoto, Kosuke OkusaAudio Representation LearningSelf-Supervised Pre-Training

  15. CASE: Complementary Articulation-Aware Speech Encoder to Enhance Speech-Driven 3D Facial Animation

    Oct 18, 2026Jaehong Myung, Seungho Eum, Taegon Kim +2Audio-Driven Facial AnimationAudio-Visual Representation Learning

  16. Native Geometry vs. Linear Recoverability: How Alignment Changes Platonic Scaling

    Oct 15, 2026Angus Hoy, Austin Lutterbach, Jasper Chong +2Neural Representation GeometryLatent Space Geometry

  17. Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters

    Oct 15, 2026Felix Nützel, Mischa Dombrowski, Luca Hagen +1Latent Space AlignmentConditional Image Generation

  18. From Plato to Aristotle: Toward a General Theory of Representation Hypotheses

    Oct 14, 2026Dai Shi, Andi Han, Xiaoyu Li +2Representation AlignmentPlatonic Representation Hypothesis

  19. Train to Stitch: Topology-Preserving Regularization for Interoperable Representations

    Oct 14, 2026Akshay Malhotra, Nicolas Zilberstein, Shahab Hamidi-RadModel StitchingLatent Space Alignment

  20. What Makes a Latent Space Shared? Direct and Recoverable Compatibility in Motion VAEs

    Oct 12, 2026Iago Brito, Walcy Rios, Lucas Fernandes +2Latent Space AlignmentMotion Representation Learning

  21. MSVAE: Rethinking Musical Semantics in Continuous Latent Spaces

    Oct 12, 2026Guobin Ma, Yuepeng Jiang, Dake Guo +15Audio Representation LearningCompositional Representation Learning

  22. Align-VAE: Aligning Attention and Geometry in VecSet VAEs for 3D Reconstruction

    Oct 10, 2026Huaizhi Qu, Mingxin Yang, Xintong Han +2Variational Autoencoders3D Reconstruction

  23. ROSETTA: Rotation Subspace Estimation for Training-free Transmodal Alignment

    Oct 9, 2026Alex Junho LeeCross-Modal AlignmentLatent Space Alignment

  24. Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining

    Oct 8, 2026Xinnian Zhao, Chia-Hua Wu, Pu Wang +1Speech Language ModelsLatent Space Alignment

  25. Shared Gaussianization: What Gaussian Regularizers Certify About Contrastive Learning, and What They Miss

    Oct 7, 2026Ruoyu Zhao, Yuting Chen, Jinheng Zhang +2Contrastive LearningMulti-View Contrastive Learning

  26. Mosquito acoustic identification at unseen recording sites: practical limits of common transfer remedies for vector surveillance

    Oct 7, 2026Yucheng Gong, Rui Zhou, Binbin Zeng +2Cross-Domain GeneralizationAudio Classification

  27. Learning Cross-Model Activation Alignments with Explicit Many-to-Many Layer Maps

    Oct 6, 2026Alina Sudakov, Guy Bar-Shalom, Fabrizio Frasca +1Latent Space AlignmentTransfer Learning