Representation Learning

Follow this topic Ask about this topic

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

804 papers133 papers in the last four weeks, up 102% on the four weeks before. 0.8% of all new papers.

CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities
May 25, 2026Junyuan Liu, Xinglei Wang, Zichao Zeng +5Representation Learning Geospatial Representation Learning
SpaceTimeLab, University College London, UK · 3DIMPact, University College London, UK · School of Resource and Environmental Sciences, Wuhan University, China +1
Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning
May 25, 2026Aleksandar Todorov, Matthia SabatelliRepresentation Learning Reinforcement Learning
University of Groningen, Groningen, The Netherlands
UNATE: UNsupervised ATomic Embedding for crystal structures property prediction
May 25, 2026Laura Solà-Garcia, Àlex Solé, Javier Ruiz-HidalgoRepresentation Learning Denoising Autoencoders
Signal Theory and Comms. Dept. UPC-Univ. Polit`ecnica de Catalunya Barcelona, Spain
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
May 25, 2026Khoi Le, Tri Cao, Phong Nguyen +5Pairwise Preference Learning Reward Modeling
National University of Singapore · VinUniversity · Nanyang Technological University
CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
May 25, 2026Pengpeng Yu, Runqing Jiang, Qi Zhang +33DGS Compression 3D Gaussian Splatting
1Sun Yat-sen University, China · 3Pengcheng Laboratory, China · 2Peking University, China
OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition
May 24, 2026Chang Chu, Qingyue Zhang, Shao-Lun Huang +1Long-Tailed Classification Shared Representation Learning
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Shenzhen Zkosemi Semiconductor Technology Co., Ltd, Shenzhen, China
QuoVLA: Quotient Space for Vision-Language-Action Models
May 24, 2026Xuan Wang, Yinan Wu, Haoran Duan +1Quantization Representation Learning
Department of Automation Tsinghua University
The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
May 24, 2026James HenryTransformer Interpretability Representation Learning
Independent Researcher
The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench
May 23, 2026Dingling Yao, Andrea Polesello, Adeel Pervez +2Representation Learning Vision Foundation Models
Institute of Science and Technology Austria
How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
May 23, 2026Rei Higuchi, Ryotaro Kawata, Akifumi Wachi +3Reward Modeling Representation Learning
The University of Tokyo · RIKEN AIP · LY Corporation
Feature Learning in Wide Neural Networks under $μ$ P: Identifiability and Sparse-Dictionary Decomposition of the Mean-Field Limit
May 23, 2026Akmal XodarevRepresentation Learning Parameter Identifiability
Independent Researcher · Tashkent, Uzbekistan
Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation
May 23, 2026Fufan Zhang, Jingxiang Wang, Xiangjie YeRepresentation Learning Occlusion Reasoning
School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China · School of Information Science and Engineering, Northeastern University, Shenyang 110819, China
Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems
May 23, 2026Imesh Ekanayake, Elham Naghizade, Jeffrey ChanAdversarial Training Representation Learning
School of Computing Technologies, RMIT University, Melbourne, VIC, Australia
Commutator-Induced Uncertainty in VAEs
May 22, 2026Tahereh Dehdarirad, Michael Felsberg, Gabriel Eilertsen +1Variational Autoencoders Disentangled Representation Learning
Computer Vision and Learning Systems (CVL), Linköping University, Sweden · Department of Science and Technology, Linköping University, Sweden
Curriculum reinforcement learning with measurable task representation learning
May 22, 2026Yongyan Wen, Siyuan Li, Mingjian Fu +3Representation Learning Curriculum RL
Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China · Fuzhou University, Fuzhou, 350108, Fujian, China · China Academy of Sciences, Beijing, 100190, China +1
RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
May 22, 2026Jinyu Yang, Cheng Yang, Junze Chen +4Representation Learning Self-Supervised Pre-Training
Beijing University Of Posts and Telecommunications Beijing, China · Peng Cheng Laboratory Shenzhen, China · China Telecom Bestpay Beijing, China +1
Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
May 22, 2026Jiayi FangRepresentation Learning World Model Learning
1Shanghai University of Finance and Economics
Feature Lottery? A Bifurcation Theory of Concept Emergence
May 22, 2026Fuming YangDynamical Systems Representation Learning
MIT
SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection
May 22, 2026Chenxu Wang, Yuxuan Li, Yunheng Li +3Open-Vocabulary Object Detection Remote Sensing Image Understanding
1VCIP, CS, Nankai University · 2NKIARI, Shenzhen Futian · 3National University of Defense Technology
STAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding
May 22, 2026Jiahe Meng, Weiming Zeng, Yueyang Li +5Cross-Modal Knowledge Distillation Representation Learning
Lab of Digital Image and Intelligent Computation, Shanghai Maritime University, Shanghai 201306, China · Department of Language Science and Technology, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China · Department of Neurology, Affiliated Lianyungang Hospital of Xuzhou Medical University, Lianyungang 222002, China +1
The TIME Machine: On The Power of Motion for Efficient Perception
May 21, 2026Mantas Skackauskas, Xinyue Hao, Laura Sevilla-LaraRepresentation Learning Video Representation Learning
School of Informatics University of Edinburgh
Human-Centered Learning Mechanics: Observable Entropy Control under Protected-Risk Constraints
May 21, 2026Kim Phuc TranRepresentation Learning Neural Network Training Dynamics
Univ. Lille, ENSAIT, ULR 2461 – GEMTEX – Génie et Matériaux Textiles, F-59000 Lille, France · International Chair in DS & XAI, International Research Institute for Artificial Intelligence and Data Science, Dong A University, Danang, Vietnam
Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning
May 21, 2026Yejin Cho, Katrin ErkRepresentation Learning Semantic Representation Learning
The University of Texas at Austin · Department of Linguistics · University of Massachusetts, Amherst
Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
May 21, 2026Julian Gutheil, Simon Hitzginger, Robert LegensteinNeural Network Generalization Disentangled Representation Learning
Graz University of Technology · Institute of Machine Learning and Neural Computation Graz University of Technology Graz, Austria
Mitigating Label Bias with Interpretable Rubric Embeddings
May 20, 2026Calvin Isley, Johann D. Gaebler, Sharad GoelRepresentation Learning Interpretable ML
Harvard Kennedy School · Harvard University · Cambridge, MA 02139 +1
HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation
May 20, 2026Shreyas Vinaya Sathyanarayana, Raja Sekhar Pappala, Deepak WarrierRepresentation Learning Molecular Representation Learning
Mstack AI Bangalore, India
Stimulus symmetries can confound representational similarity analyses
May 20, 2026Farhad Pashakhanloo, Jacob A. Zavatone-VethRepresentational Similarity Analysis Representation Learning
Center for Brain Science and 2Society of Fellows Harvard University, Cambridge, MA, USA
A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation
May 20, 2026Yan Li, Yuewen Sun, Shaoan Xie +4Representation Learning Causal Representation Learning
1Mohamed bin Zayed University of Artificial Intelligence · 2Carnegie Mellon University
Supervised Latent Restructuring for Small-Data Quantum Learning in Plant Phenomics
May 19, 2026Alakananda Mitra, David H. Fleisher, Vangimalla Reddy +1Plant Phenotyping Representation Learning
Nebraska Water Center, IANR University of Nebraska–Lincoln Lincoln, NE 68588 · Adaptive Cropping Systems Laboratory USDA-ARS Beltsville, MD 20705 · Nebraska Water Center, DWFI University of Nebraska–Lincoln Lincoln, NE 68588
Atoms of Thought: Universal EEG Representation Learning with Microstates
May 19, 2026Xinyang Tian, Ruitao Liu, Ziyi Ye +3Electroencephalography Representation Learning
Institute for Interdisciplinary Information Sciences, Tsinghua University Beijing, China · Institute of Trustworthy Embodied AI, Fudan University Shanghai, China · Beijing Five Seasons Medical Technology Co., Ltd. Beijing, China

May 25, 2026J/K move · Enter open · S save

CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities

Junyuan Liu, Xinglei Wang, Zichao Zeng, Jiazhuang Feng+4

SpaceTimeLab, University College London, UK · 3DIMPact, University College London, UK · School of Resource and Environmental Sciences, Wuhan University, China+1

Representation Learning Geospatial Representation Learning Data Contamination Urban Representation Learning

Open paper AskPDF arXiv

Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two cities and tasks and relying on random splits that introduce spatial leakage, leading to inflated performance and weak support for cross-location generalization and fair comparison. To address this, we propose CityRep, a unified benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits. CityRep consists of three key components: (1) a spatial unit-agnostic evaluation framework that supports heterogeneous urban representations through a standardized alignment module; (2) a unified evaluation protocol using block-based spatial splits to mitigate spatial leakage and enable rigorous model comparison; and (3) an extensible multi-city, multi-task benchmark suite spanning 8 cities and 8 tasks across regression, classification, and distribution prediction. We evaluate 11 representative urban representation models. Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings. We also observe substantial variability across cities and tasks, underscoring the need for generalization-aware evaluation. CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison and support future research in urban representation learning towards urban foundation models.