Representation Learning
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
855 papers91 papers in the last four weeks, down 14% on the four weeks before. 0.6% of all new papers.
Large Payments Model
Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals
Learning Rate Transfer and Feature Learning Across Depth for Constrained Spectral Optimizers: Complete Scion
Beyond Foreign-Key Connectivity: Semantic Relationship Representation for Relational Deep Learning
ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models
DeRep: Learning Depth Representations for End-to-End Navigation in Cluttered Environments
Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation
Rethinking Radar 3D Perception: Representation Learning from Raw Spectra
Are UFOs Real? Introducing Unified Factored Organizers
PAIR: Proprioception-Aligned Image-Ray Representations for Viewpoint-Robust Manipulation
Identifiable alignment of unpaired representations
Unified Factored Representations Resist Catastrophic Forgetting
Elastic Representations via Hyperbolic Geometry
The Delta Gap: Cellular World Models for Perturbation Response Prediction Are Far Harder Than Global Correlation Implies
Embedding Predictive Adaptation and Refinement for Multi-Modal Industrial Anomaly Detection
Deep Learning Theory through the Lens of Statistical Physics: A Topical Review
LEF-JEPA: Denoising-Trained Latent Energy Fields for Spatial Representation Learning
Self-Supervised Diffusion Models for Handwritten Signature Verification via Ruin Reconstruction
ruins'' signatures through severe crumpling, obliterating their structural integrity and writing styles. A visual encoder is employed to capture crucial handwriting patterns from intact signature regions, guiding the denoiser to reconstruct the ruined'' portions and learning meaningful representations. Additionally, we introduce a pyramidal feature aggregation module (PFAM) to bridge the visual encoder and denoiser, enhancing representation quality via hierarchical aggregation and modulation. Extensive experiments on multilingual signature datasets demonstrate that SigDiffuser significantly outperforms both state-of-the-art SSL methods and HSV models. We further show that increasing the crumpling severity on signatures effectively improves representation quality. Notably, our work demonstrates that extreme destruction, coupled with self-supervised diffusion models, can yield superior signature representation compared to traditional mild deformations, paving new avenues for HSV and other biometric domains. Code will be publicly available.