Visual Representation Learning

Follow this topic Ask about this topic

Visual representation learning studies how to turn images and video into features that preserve information useful for tasks such as classification, segmentation, retrieval, and robotic control. Common approaches include contrastive and masked-image learning, predictive methods such as joint-embedding models, generative objectives, and supervision from language, geometry, or action. Vision foundation models are increasingly evaluated beyond ImageNet classification, on dense prediction, robustness to visual shifts, compositional reasoning, and real-world manipulation. A central tension is how to make features broadly transferable and efficient while retaining fine spatial detail, task-relevant information, and reliability under distribution changes.

Latest papers

224 papers26 papers in the last four weeks, down 7% on the four weeks before. 0.2% of all new papers.

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
Mar 25, 2026Changyu Liu, James Chenhao Liang, Wenhao Yang +6Visual Representation Learning Diffusion Models
University of Missouri–Kansas City · U. S. Naval Research Laboratory · Lamar University +5
SilLang: Improving Gait Recognition with Silhouette Language Encoding
Mar 25, 2026Ruiyi Zhan, Guozhen Peng, Canyu Chen +2Gait Recognition Visual Representation Learning
Beihang University · Tsinghua University
Vision-based Deep Learning Analysis of Unordered Biomedical Tabular Datasets via Optimal Spatial Cartography
Mar 24, 2026Sakib Mostafa, Tarik Massoud, Maximilian Diehn +2Tabular Prediction Tabular Representation Learning
Department of Radiation Oncology, Stanford University, Stanford, California, USA · Department of Radiology, Stanford University, Stanford, California, USA · Institute for Stem Cell Biology and Regenerative Medicine, Stanford University, Stanford, California, USA +1
Efficient Universal Perception Encoder
Mar 23, 2026Chenchen Zhu, Saksham Suri, Cijo Jose +8Visual Representation Learning Vision Foundation Models
Meta Reality Labs · FAIR at Meta
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
Mar 23, 2026Byungwoo Jeon, Dongyoung Kim, Huiwon Jang +2Visual Representation Learning 3D Spatial Reasoning
KAIST · RLWRLD · NAVER Cloud
The Universal Normal Embedding
Mar 23, 2026Chen Tasker, Roy Betser, Eyal Gofer +2Latent Space Alignment Visual Representation Learning
Viterbi Faculty of Electrical and Computer Engineering Technion - Israel Institute of Technology
SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation
Mar 22, 2026Wen Jiang, Kangyao Huang, Li Wang +9Visual Representation Learning 3D Spatial Reasoning
School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China · Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · Chongqing Innovation Center, Beijing Institute of Technology, Chongqing 401120, China +5
Efficiency Follows Global-Local Decoupling
Mar 20, 2026Zhenyu Yang, Gensheng Pei, Tao Chen +4Efficient Neural Network Inference Visual Representation Learning
Nanjing University of Science and Technology · State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery · Department of Electrical and Computer Engineering, Sungkyunkwan University +2
M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking
Mar 18, 2026Qiangqiang Wu, Tianyu Yang, Bo Fang +4Point Tracking Vision Foundation Model Adaptation
Department of Computer Science, City University of Hong Kong, China · Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA · Meituan, Shenzhen, China +2
Toward Deep Representation Learning for Event-Enhanced Visual Autonomous Perception: the eAP Dataset
Mar 17, 2026Jinghang Li, Shichao Li, Qing Lian +3Autonomous Driving Perception Autonomous Driving Datasets
Neuromorphic Automation and Intelligence Lab (NAIL) at School of AI & Robotics, Hunan University, Changsha 410082, China. · ByteDance, Shenzhen 518063, China. · Zhuoyu Technology, Shenzhen 518055, China.
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Mar 15, 2026Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar +6Self-Supervised Visual Representation Learning Visual Representation Learning
FAIR at Meta · Universidad de Zaragoza
DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images
Mar 15, 2026Umar Marikkar, Syed Sameed Husain, Muhammad Awais +1Vision Transformer Visual Representation Learning
University of Surrey
RAE-NWM: Navigation World Model in Dense Visual Representation Space
Mar 10, 2026Mingkun Zhang, Wangtian Shen, Fan Zhang +3Visual Navigation World Model Learning
Department of Precision Instrument, Tsinghua University, Beijing, China · University of Rochester, Rochester, NY, USA · Beijing Information Science and Technology University, Beijing, China
Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM
Mar 9, 2026Junyuan Mao, Qiankun Li, Linghao Meng +5Large Vision-Language Models Fine-Grained Visual Perception
National University of Singapore · Nanyang Technological University
MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval
Mar 7, 2026Fengbin Zhu, Zijing Cai, Yuzhe Wang +5Visual Document Retrieval Visual Representation Learning
National University of Singapore, Singapore · University of Science and Technology of China, China · Hefei University of Technology, China
Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation
Mar 5, 2026Boyu Han, Qianqian Xu, Shilong Bao +4Visual Representation Learning Self-Supervised Visual Representation Learning
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · School of Computer Science and Tech., University of Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence +3
Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language Models
Mar 3, 2026Haruto Yoshida, Keito Kudo, Yoichi Aoki +4Vision-Language Models Large Vision-Language Models
Tohoku University · Human Informatics Labs., NTT, Inc.
Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
Mar 3, 2026Chao Li, Tianhong Li, Sai Vidyaranya Nuthalapati +9T2I Generation Visual Representation Learning
MIT Computer Science & Artificial Intelligence Laboratory · Meta AI
Social-JEPA: Emergent Geometric Isomorphism
Feb 28, 2026Youjin WangRepresentation Learning Visual Representation Learning
Renmin University of China
Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training
Feb 28, 2026Quan Kong, Yanru Xiao, Yuhao Shen +1Visual Representation Learning Efficient ViTs
Zhejiang University, Hangzhou, China · Amazon Web Services, USA
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
Feb 27, 2026Arnas Uselis, Andrea Dittadi, Seong Joon OhNeural Representation Geometry Visual Representation Learning
Tübingen AI Center, University of Tübingen · Helmholtz · Technical University of Munich
Through BrokenEyes: How Eye Disorders Impact Face Detection?
Feb 26, 2026Prottay Kumar AdhikaryVisual Representation Learning
Indian Institute of Technology Delhi, Delhi, India
Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery
Feb 26, 2026Minh Kha Do, Wei Xiang, Kang Han +5Remote Sensing VLMs Remote Sensing Image Understanding
La Trobe University, Melbourne, VIC 3086, Australia · Cisco Research, San Jose, CA, USA
Vision Transformers Need More Than Registers
Feb 25, 2026Cheng Shi, Yizhou Yu, Sibei YangVision Transformer Visual Representation Learning
School of Computing and Data Science, The University of Hong Kong · Sun Yat-sen University
Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models
Feb 24, 2026Qing Zhang, Xuesong Li, Jing ZhangVision Foundation Models Visual Spatial Reasoning
1The Australian National University · 2CSIRO
UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models
Feb 23, 2026Manish Kumar Govind, Dominick Reilly, Pu Wang +1Vision-Language-Action Models Latent Action Learning
All authors are with the Department of Computer Science, University of North Carolina at Charlotte, NC, USA.
Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation
Feb 23, 2026Filip Wolf, Blaž Rolih, Luka Čehovin ZajcRemote Sensing Image Understanding Visual Representation Learning
University of Ljubljana, Faculty of Computer and Information Science, Slovenia
JEPA-Bisim: Learning Robust Visual Representations for Planning with Joint-Embedding Predictive World Models
Feb 20, 2026Leonardo F. Toso, Davit Shadunts, Yunyang Lu +5Visual Representation Learning World Models for Robotics
Department of Electrical Engineering, Columbia University, New York, USA. · Capital One, USA.
Coverage-aware Semantic Representation Learning for Underrepresented Visual Concepts
Feb 18, 2026Sakib Ahammed, Xia Cui, Wenqi Lu +4Representation Learning Visual Representation Learning
Department of Computing and Mathematics, Manchester Metropolitan University The Dalton Building, Chester Street, M1 5GD Manchester
Are Object-Centric Representations Better At Compositional Generalization?
Feb 18, 2026Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Maximilian Seitzer +4Compositional Generalization Object-Centric Representation Learning
Technical University of Munich · Helmholtz AI, Munich · KTH Royal Institute of Technology +2

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

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning

Changyu Liu, James Chenhao Liang, Wenhao Yang, Yiming Cui+5

University of Missouri–Kansas City · U. S. Naval Research Laboratory · Lamar University+5

Visual Representation Learning Diffusion Models Diffusion Transformer Diffusion Timestep Scheduling

Open paper AskPDF arXiv

Diffusion models have significantly reshaped the field of generative artificial intelligence and are now increasingly explored for their capacity in discriminative representation learning. Diffusion Transformer (DiT) has recently gained attention as a promising alternative to conventional U-Net-based diffusion models, demonstrating a promising avenue for downstream discriminative tasks via generative pre-training. However, its current training efficiency and representational capacity remain largely constrained due to the inadequate timestep searching and insufficient exploitation of DiT-specific feature representations. In light of this view, we introduce Automatically Selected Timestep (A-SelecT) that dynamically pinpoints DiT's most information-rich timestep from the selected transformer feature in a single run, eliminating the need for both computationally intensive exhaustive timestep searching and suboptimal discriminative feature selection. Extensive experiments on classification and segmentation benchmarks demonstrate that DiT, empowered by A-SelecT, surpasses all prior diffusion-based attempts efficiently and effectively.