Representation Learning

Follow this topic Ask about this topic

Recent momentum

-58%

19 papers in the last 28 days · 0.3% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

7 new papers

A weekly snapshot of new work published in Representation Learning.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Representation Learning.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Representation Learning.

301 papers

Latest in Representation Learning

Browse all topics →

S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
Jun 17, 2026Georgios Ioannides, Adrian Kieback, Judah Goldfeder +5Sphere-Jepa Representation Learning
Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion
Jun 16, 2026Somjit Nath, Jackson J Cone, Derek Nowrouzezahrai +1Neurophysiological Correlates Learning Dynamics
Dimensionality Controls When Modularity Helps in Continual Learning
Jun 16, 2026Kathrin Korte, Christian Medeiros Adriano, Joachim Winther Pedersen +2Efficient Continual Learning Continual Learning Methods
Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations
Jun 16, 2026Takaya KawakatsuTabular Learning Multi--Task Learning
Beer-Lambert Guided Representation Learning for Unsupervised Anomaly Detection in Sub-THz Food Inspection Images
Jun 15, 2026Gyutae Hwang, Sang Jun LeeAnomaly Detection Detection Framework
Scalable and Interpretable Representation Alignment with Ordinal Similarity
Jun 15, 2026Diogo Soares, Pankhil Gawade, Andrea Dittadi +1Semantic Similarity Metrics Representation Learning
Sensor-Conditioned Representation Learning via Scene-Relevant Observation Quotients
Jun 15, 2026Yan Jiao, Pin-Han Ho, Limei PengRepresentation Learning Observation
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
Jun 14, 2026Ninad Daithankar, Alexi Gladstone, Yann LeCun +1Self-Supervised Representations Photometric Supervision
ttda704 at SemEval-2026 Task 4: Modeling Narrative Structures via Pseudonymization and Multi-View Sentence Alignment
Jun 14, 2026Tai Tran Tan, An Dinh ThienNarratives Geo-Contextual Alignment
InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset
Jun 14, 2026Zhenyu YuBackdoor Attacks Training-Free Inference Framework
CAP: Towards PPG Universal Representation Learning with Patient-level Supervision
Jun 13, 2026Chenyang He, Xinyi Shao, Shun Huang +4Remote Photoplethysmography Multimodal Clinical Data
RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning
Jun 13, 2026Jinhan Liu, Mahsa ShoaranFunctional Networks Temporal Deep Learning Framework
Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G
Jun 12, 2026Chenyu Zhang, Xinchen Lyu, Chenshan Ren +2Channel State Information Wireless Foundation Models
JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics
Jun 12, 2026Guillaume Letellier, Antonin Vacheret, Frédéric JurieHigh Energy Physics Joint-Embedding Predictive Architectures
The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning
Jun 11, 2026Ayushman Trivedi, Bhavika MelwaniCatastrophic Forgetting Continual Learning Methods
Towards Effective Waste Segmentation for Automated Waste Recycling in Cluttered Background
Jun 11, 2026Mamoona Javaid, Mubashir Noman, Abdul Hannan +3Waste Representation Learning
Detecting Explanatory Insufficiency in Learned Representations: A Framework for Representational Vigilance
Jun 11, 2026Jacques Raynal, Pierre Slangen, Elsa Raynal +1Representation Learning Visual Representations
A Stationary (and Therefore Compatible) Representation is All You Need
Jun 10, 2026Niccolò Biondi, Federico Pernici, Simone Ricci +1Representation Learning Representation Space
One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data
Jun 9, 2026Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers +4Spatio-Temporal Transformers Time Series
Efficient RWKV-based Representation Learning for 3D Point Clouds
Jun 9, 2026Yun Liu, Xuefeng Yan, Liangliang Nan +5Geometry-Aware Foundation Model Representation Learning
Spatiotemporal Graph Transformer for 3D Neighborhood Interaction and Quality Prediction in Metal Additive Manufacturing
Jun 8, 2026Joyce Karen Pelaez, Siqi Zhang, Hoo Sang KoAdditive Manufacturing Temporal Graph Neural Networks
SMI: Efficient Self-Supervised Learning via Mutual-Information-Inspired Dependency Optimization
Jun 6, 2026Pritam Mishra, Coloma Ballester, Dimosthenis KaratzasSelf-Supervised Representation Learning
Bootstrap Theory of Representational Emergence: Explanatory Insufficiency as a Driver of Representation Learning and World Models
Jun 5, 2026Jacques Raynal, Pierre Slangen, Elsa Raynal +1Representation Learning Emergence
Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory
Jun 4, 2026Sam Buchanan, Druv Pai, Peng Wang +1Representation Learning Black Box
Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
Jun 4, 2026Johan Obando-Ceron, Lu Li, Scott Fujimoto +3Multi-Task Reinforcement Learning Deep Reinforcement Learning
Balancing Image Compression and Generation with Bootstrapped Tokenization
Jun 4, 2026Haozhe Chi, Jinghan Li, Hao Jiang +4Tokenization Self-Supervised Reconstruction Method
Environment-Robust Representation Learning with Empirical Bayes
Jun 3, 2026Yuli Slavutsky, Matthew Shen, Bohan Wu +1Bayesian Latent Variable
BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning
Jun 3, 2026Luca Thale-Bombien, Jan Ewald, Ralf König +1Hyperparameter Optimization Multi-Omic Framework
RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities
Jun 3, 2026Vasiliki Rizou, Pascal Frossard, Dorina ThanouMulti-Modal Representation Learning Representation Learning
CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection
Jun 3, 2026Roberto Di Via, Irina Voiculescu, Francesca Odone +1One-Shot Medical Landmark Detection Medical Imaging Datasets
StrokeTimer: Robust Representation Learning for Ischemic Stroke Onset-Time Estimation from Non-contrast CT
Jun 3, 2026Weiru Wang, Susanne G. H. Olthuis, Elizaveta Lavrova +4Stroke Neuroimaging Models
Hyperparameter Learning for Latent Factorization of Tensors for Representation Learning to Large-scale Dynamic Weighted Directed Network
Jun 3, 2026Yaqian Zhan, Jialan He, Tianzhu ChenHyperparameter Optimization Model Weights
OpenRFM: Dissecting Relational In-Context Learning
Jun 3, 2026Zhikai Chen, Junyu Yin, Jialiang Gu +5Relational Deep Learning In-Context Learning
NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense
Jun 2, 2026Zhongyang Lin, Ziran Zhao, Feifei Zhai +1Higher Attack Success Rates Prompt-Level Mitigations
Bayes-Sufficient Representations in Supervised Learning
Jun 2, 2026Vasileios SevetlidisBayesian Supervised Learning
Learning Coherent Representations: A Topological Approach to Interpretability
Jun 1, 2026Sigurd Gaukstad, Melvin Vaupel, Valdemar Kargård Olsen +2Model Interpretability Representation Learning
Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models
Jun 1, 2026Alexander GuhaRepresentational Capacity Representation Learning
From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
Jun 1, 2026Yuming Zhao, Junhui Hou, Qijian Zhang +2Semantic-Geometric Representations 3D Geometry
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
Jun 1, 2026Manu Srinath Halvagal, Sebastian Lee, SueYeon ChungDeep Reinforcement Learning Representation Learning
Flexible Online Representation Learning Based on Similarity Matching
Jun 1, 2026Shagesh Sridharan, Yanis Bahroun, Anirvan M. SenguptaManifold Learning Method Representation Learning
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
May 30, 2026Fuyuan Qian, Menglong Zhang, Song Wang +1Offline Reinforcement Learning Sparse Rewards
Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
May 30, 2026Jiafu Huang, Chao Peng, Chenyang Xu +7Implicit Neural Representations Representation Learning
UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
May 29, 2026Hanyu Li, Yi-Ping Hsu, Aditya Mantha +17Ranking Cross-Attention
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
May 29, 2026Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad +1Joint-Embedding Predictive Architectures Representation Learning
Effective Biological Representation Learning by Masking Gene Expression
May 29, 2026Kian Kenyon-Dean, Alina Selega, Ihab Bendidi +5Spatial Transcriptomics Single-Cell Rna Sequencing
Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects
May 29, 2026Artur Szałata, Olga Novitskaia, Maiia Shulman +3Single-Cell Perturbation Prediction Spatial Transcriptomics
The Terminal Representation in Reinforcement Learning
May 29, 2026Amir Esterhuysen, Anders JonssonRepresentation Learning Successor Representations
HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model
May 29, 2026Xiang Zhu, Puzhen Yuan, Yichen Liu +1Vision-Language-Action Models Latent Actions
Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
May 29, 2026Willian T. Lunardi, Samridha Shrestha, Martin AndreoniOut-Of-Distribution Detection Time-Frequency
HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning
May 29, 2026Md Aminur Hossain, Ayush V. Patel, Sanjay K. Singh +1Remote Sensing Joint-Embedding Predictive Architectures
Learning to Perceive the World Through Control: Empowerment-Based Representation Learning
May 28, 2026Mahsa Bastankhah, Sophie Broderick, Benjamin EysenbachControl System Operator Learning Representation Learning
Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning
May 28, 2026Yujin Jeong, Noelle Jung, Brian Y. C. LeungFinancial Sentiment Analysis Multivariate Forecasting
Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption
May 28, 2026Yankai Chen, Hanrong Zhang, Bowei He +2Robust Optimization Corrupted Observations
Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
May 28, 2026Tong Ye, Hang Yu, Tengfei Ma +6Domain-Specific Language Automated Synthesis Techniques
A Geometric View of SRC: Learning Representations for Stable Residual Inference
May 28, 2026Vangelis P. OikonomouResidual Learning Bias Learning
Learning Representations from 3D Gaussian Splats
May 28, 2026Julia Farganus, Krzysztof Żurawicki, Arkadiusz Gaweł +23D Gaussian Splats 3D Scene Understanding
LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation
May 28, 2026Shali Jiang, Hua Zheng, Boyang Liu +40Knowledge Distillation Wireless Foundation Models
Learning Robust and Task-Invariant Functional Representation from fMRI through Siamese Self-Supervised Learning
May 27, 2026Jiyao Wang, Peiyu Duan, Nicha C. Dvornek +4Neuroimaging Models Brain Magnetic Resonance Imaging
Measure-to-measure Regression with Transformers
May 27, 2026Matthew Vandergrift, Martha White, Yury Polyanskiy +2Representation Learning Transformer Architectures
Information-theoretic Multimodal Representation Learning for Electrocardiogram Signals
May 26, 2026Phu X. Nguyen, Konstantinos Kontras, Wei Dai +5Electrocardiogram Classification Multimodal Physiological Signals

Jun 17, 2026 · cs.SDJ/K move · Enter open · S save

S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning

Georgios Ioannides, Adrian Kieback, Judah Goldfeder, Linsey Pang+4

Carnegie Mellon University · James Silberrad Brown Center for AI · Amazon GenAI · Columbia University · Northeastern University

Self-supervised speech encoders are predominantly trained by predicting discrete hard cluster IDs at masked positions, a recipe that collapses acoustic ambiguity at category boundaries and requires interrupting training to re-cluster the entire corpus between iterations. We introduce S-JEPA, a JEPA-style encoder-predictor pair trained to match the soft posteriors of a Gaussian Mixture Model at masked positions via KL divergence. Training runs as one continuous optimization trajectory in two phases: a fixed GMM over MFCC features, then an online GMM over encoder features, with the input layer selected adaptively from a label-free signal, removing both the offline re-cluster step and the hand-tuned choice of which transformer layer to cluster on. Under the SUPERB protocol, S-JEPA achieves the lowest WER among evaluated SSL methods below 90M parameters and matches HuBERT-Base on emotion recognition at roughly half its parameter count, establishing a new Pareto frontier without offline re-clustering or teacher distillation. An analysis of the predictor's per-frame entropy on held-out speech reveals a bimodal distribution with a substantial minority of frames near the entropy of a perfect two-cluster tie, providing direct empirical evidence that the soft-target objective preserves the acoustic ambiguity that hard targets would collapse. Code is available at https://github.com/gioannides/s-jepa.

Sphere-Jepa Representation Learning Acoustic Image Clustering Gaussian Mixture Models Multi-Teacher Distillation

Open paper Ask about it PDF