Overview

Representation learning studies how to turn raw data—such as images, text, graphs, time series, and sensor signals—into features that make important patterns easier to use. Common approaches include contrastive and masked prediction, autoencoders, predictive latent models, sparse coding, and methods that impose structure such as geometry, hierarchy, or disentangled subspaces. Good representations can reduce label needs and support transfer across tasks, domains, and modalities, with evaluations spanning linear probes, retrieval, classification, and downstream control. A central tension is that compression and invariance can discard information a later task needs, so no single objective or representation geometry works best across settings.

Latest papers

CardsList

799 papers130 papers in the last four weeks, up 97% on the four weeks before. 0.8% of all new papers.

  1. Beyond Task-Driven Features for Object Detection

    Apr 4, 2026Meilun Zhou, Alina ZareObject DetectionRepresentation Learning

  2. Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations

    Apr 4, 2026Meilun Zhou, Alina ZareRepresentation LearningMulti-Task Learning

  3. Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval

    Apr 4, 2026Jun Li, Xuhang Lou, Jinpeng Wang +4Cross-Modal RetrievalInformation Retrieval

  4. NearID: Identity Representation Learning via Near-identity Distractors

    Apr 2, 2026Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey +2Representation LearningVisual Representation Learning

  5. On Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Measurements

    Apr 2, 2026George Sebastian, Philipp Berthold, Bianca Forkel +2Representation LearningMillimeter-Wave Radar

  6. Representation Selection via Cross-Model Agreement using Canonical Correlation Analysis

    Apr 1, 2026Dylan B. Lewis, Jens Gregor, Hector Santos-VillalobosCanonical Correlation AnalysisRepresentation Learning

  7. Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis

    Mar 30, 2026Yijin Wang, Fandi Sun, Haoyu WenAspect-Based Sentiment AnalysisRepresentation Learning

  8. SPROUT: A Scalable Diffusion Foundation Model for Multi-Crop Plant Phenotyping

    Mar 29, 2026Shuai Xiang, James Burridge, Shouyang Liu +4Agricultural Image AnalysisPlant Phenotyping

  9. Towards Intrinsic-Aware Monocular 3D Object Detection

    Mar 28, 2026Zhihao Zhang, Abhinav Kumar, Xiaoming Liu3D Object DetectionMonocular 3D Object Detection

  10. Silhouette Loss: Differentiable Global Structure Learning for Deep Representations

    Mar 27, 2026Matheus Vinícius Todescato, Joel Luís CarboneraRepresentation LearningMetric Learning

  11. HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network

    Mar 27, 2026Mingyu Zhang, Zixu Li, Zhiwei Chen +5Composed Image RetrievalCross-Modal Feature Matching

  12. Exploring How Fair Model Representations Relate to Fair Recommendations

    Mar 25, 2026Bjørnar Vassøy, Benjamin Kille, Helge LangsethFairness in Recommender SystemsAlgorithmic Fairness

  13. KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits

    Mar 25, 2026Peng Xu, Yapeng Li, Tinghuan Chen +2Representation LearningGraph Representation Learning

  14. Minimal Sufficient Representations for Self-interpretable Deep Neural Networks

    Mar 25, 2026Zhiyao Tan, Liu Li, Huazhen LinNeural Network InterpretabilityRepresentation Learning

  15. Deep Neural Regression Collapse

    Mar 25, 2026Akshay Rangamani, Altay UnalRepresentation Learning

  16. Generalizing Dynamics Modeling More Easily from Representation Perspective

    Mar 24, 2026Yiming Wang, Zhengnan Zhang, Genghe Zhang +7Dynamical SystemsLatent Dynamics Modeling

  17. PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts

    Mar 22, 2026Neeladri Bhuiya, Shib Sankar Dasgupta, Andrew McCallum +1LLM EvaluationRepresentation Learning

  18. Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models

    Mar 22, 2026Qifan Li, Xingyu Zhou, Jinhua Zhang +2Latent-Space RegularizationLatent Diffusion Models

  19. Discriminative Representation Learning for Clinical Prediction

    Mar 21, 2026Yang Zhang, Li Fan, Samuel Lawrence +1Representation LearningClinical Outcome Prediction

  20. Cross-Granularity Representations for Biological Sequences: Insights from ESM and BiGCARP

    Mar 21, 2026Hanlin Xiao, Rainer Breitling, Eriko Takano +1Representation LearningProtein Representation Learning

  21. Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models

    Mar 21, 2026Enguang Wang, Qiang Wang, Yuanchen Wu +5Multimodal Large Language ModelsRepresentation Learning

  22. IBCapsNet: Information Bottleneck Capsule Network for Noise-Robust Representation Learning

    Mar 21, 2026Canqun Xiang, Chen Yang, Jiaoyan ZhaoNeural Network RobustnessRepresentation Learning