Overview

Representation alignment asks when different models, modalities, or groups of users encode the same useful structure, and whether those representations can support transfer or cooperation. Researchers compare spaces with methods such as CKA, RSA, nearest-neighbor overlap, and Procrustes alignment, or train mappings with contrastive losses, distillation, and lightweight adapters. Applications range from vision-language models and brain-signal decoding to federated learning, diffusion generation, and transferring capabilities between language models. A central open tension is that similar geometry or high alignment scores do not necessarily mean models behave alike: agreement may hold for broad relationships but fail for fine details or useful information transfer.

Latest papers

CardsList

119 papers6 papers in the last four weeks, down 79% on the four weeks before. 0.0% of all new papers.

  1. Classical structural priors improve neural molecular representations in molecule language models

    Nov 16, 2026Donghyeok Lee, Sangkwon Park, Munyoung Chang +1Molecular Representation LearningChemical Language Models

  2. Interpretability Is Not Model-Specific

    Nov 9, 2026Marcus Armstrong, Navid Ayoobi, Pradham Mummaleti +2Interpretable MLMechanistic Interpretability

  3. Identifiable alignment of unpaired representations

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

  4. The Platonic Brain: Representational Convergence in EEG Foundation Models

    Nov 3, 2026Nicolas Waehner, Enzo Tagliazucchi, Jacobo Sitt +3Representation AlignmentPlatonic Representation Hypothesis

  5. Thought-deciphering via hierarchical EEG-to-text alignment

    Nov 2, 2026Xiaopeng Mao, Morten Mørup, Xin Xu +2EEG-to-Text DecodingBrain-Computer Interfaces

  6. Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers

    Nov 2, 2026Raphael Maser, Siddhartha Gairola, Sukrut Rao +1ViT ExplainabilityTransformer Interpretability

  7. Latent Bridge: From Video Latents to 3D Geometry via Feature Alignment

    Oct 20, 2026Shuai Zhang, Zhanpeng Ouyang, Zhengqing Chen +73D ReconstructionFeed-Forward 3D Reconstruction

  8. Relational Spatial Alignment for Vision-Language-Action Models

    Oct 17, 2026Chaoran Zhu, Hengyi Wang, Chenglin Cui +3Representation Alignment3D Spatial Reasoning

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

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

  10. Semantic Alignment of EEG and Text: A Contrastive Learning Framework for Decoding Imagined Speech

    Oct 14, 2026Shahryar G. Namdari, Francesco Iacomi, Riccardo Barbieri +1EEG DecodingEEG-to-Text Decoding

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

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

  12. Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching

    Oct 14, 2026Xiaocong Yang, Xuanyu Meng, Yuji Zhang +2Neuro-Symbolic AIRepresentation Alignment

  13. LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers

    Oct 13, 2026Zipeng Wang, Anping Xiong, Jing Zhang +17Diffusion-Based Image GenerationDiffusion Transformer

  14. HiPPT: Physiology-Grounded Wearable PPG Representation Learning via Multi-Scope Text Alignment

    Oct 10, 2026Jiaqi Wang, Wei Chen, Xiaoyu Li +7Representation LearningPhotoplethysmography

  15. CoVA: Composing VAE Representations for Generative Learning

    Oct 9, 2026Zhaowei Chen, Yikai Ge, Linze Li +2Diffusion-Based Image GenerationDiffusion Transformer

  16. Learning Kilometer-Scale Weather Prediction with Global-Regional Alignment

    Oct 8, 2026Guowen Li, Yang Liu, Yujie Wang +5Weather DownscalingWeather Forecasting

  17. Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?

    Oct 7, 2026Zihao Zhang, Haochen Tian, Tianyu Li +5End-to-End Autonomous DrivingRepresentation Alignment

  18. A theory of platonic representations in language models

    Oct 5, 2026Darshil Doshi, Wenjie Zhou, Corinna Elena Wegner +3Belief PropagationMultilingual Language Models

  19. On Representational Alignment among Embodied Agents

    Oct 2, 2026Fulvio MastrogiovanniRepresentation AlignmentEmbodied AI

  20. PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion

    Sep 30, 2026Lehan Yang, Daiqing Qi, Wenhao Zhang +9Diffusion Model AlignmentDiffusion Transformer

  21. Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning

    Sep 28, 2026Hyunwoo Yoo, Cassie Huang, Haebin Shin +2LLM PlanningSymbolic Planning

  22. SignFLIP: A Unified Model for Sign Language Translation and Generation via Stage-wise Alignment at Scale

    Sep 28, 2026Zhaoyi An, Sihan Tan, Youngbae Hwang +2Sign Language TranslationRepresentation Alignment

  23. What Visual Generators Need from Teachers: Rethinking Representation Alignment

    Sep 28, 2026Yongcong Wang, Hingchin Chen, Mingyu Fan +6Diffusion Model AlignmentDiffusion Transformer

  24. A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning

    Sep 27, 2026Gustav Wagner Zakarias, Zheng-Hua TanFine-TuningBilevel Optimization

  25. Can Circuit Alignment Predict OOD Generalization?

    Sep 25, 2026Ayan Banerjee, Abhra Chaudhuri, Josep Llados +2Distribution Shift RobustnessOOD Generalization