Visual Representation Learning

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 367% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 147

All topics

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
May 28, 2026Jusuk Lee, Seungjae Lee, Jonghun Shin +6Cross-Modal Learning Cross-Modal Representation Learning
Seoul National University · University of Maryland, College Park · Georgia Institute of Technology
Deep Psychovisual Image Representations
May 28, 2026Wendi Ma, Aryaman Sharma, Wei Dai +1Visual Representation Learning Frequency-Domain Feature Learning
School of EECS, The University of Queensland
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
May 27, 2026Joséphine Raugel, Maximilian Seitzer, Marc Szafraniec +6Backpropagation Visual Representation Learning
Meta AI · Ecole Normale Supérieure, PSL University
Structure over Pixels: Learning Variable-Length Visual Programs
May 26, 2026Piotr Wyrwiński, Kacper Dobek, Krzysztof KrawiecVisual Representation Learning Image Tokenization
Institute of Computing Science Poznan University of Technology, Poznan, Poland
Uncertainty-DTW for Sequences and Visual Tokens
May 24, 2026Lei Wang, Syuan-Hao Li, Yongsheng Gao +1Dynamic Time Warping Visual Representation Learning
School of Engineering and Built Environment, Electrical and Electronic Engineering, Griffith University · School of Computer Science and Engineering, University of New South Wales
Vision Transformers Need Better Token Interaction
May 22, 2026Linxiang SuVisual Representation Learning Vision Transformer
University of Szeged
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
May 22, 2026Jorge Chang Ortega, Bastien Le Lan, Thomas Serre +1Visual Representation Learning Energy-Based Models
ANITI · Brown University, ANITI · CNRS, ANITI
Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology
May 21, 2026Nils LeuteneggerRepresentational Similarity Analysis Visual Representation Learning
Independent Researcher, Switzerland
TextTeacher: What Can Language Teach About Images?
May 21, 2026Tobias Christian Nauen, Stanislav Frolov, Brian Bernhard Moser +3Cross-Modal Knowledge Distillation Visual Representation Learning
RPTU University Kaiserslautern-Landau · German Research Center for Artificial Intelligence (DFKI)
RiT: Vanilla Diffusion Transformers Suffice in Representation Space
May 21, 2026Le Zhang, Ning Mang, Aishwarya AgrawalFlow Matching Visual Representation Learning
Mila – Québec AI Institute, UdeM · Utrecht University · Canada CIFAR AI Chair
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
May 20, 2026Gene Tangtartharakul, Katherine R. StorrsVisual Representation Learning Mixture of Experts
School of Psychology · University of Auckland · Auckland, New Zealand
Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
May 19, 2026Julien Colin, Lore Goetschalckx, Nuria Oliver +1Visual Representation Learning Vision Foundation Models
ELLIS Alicante, Spain · imec, Leuven, Belgium · Brown University, USA
KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision
May 19, 2026Maya Yanko, Yoli ShavitVisual Representation Learning Visual Place Recognition
Faculty of Engineering Bar-Ilan University Ramat Gan, Israel
PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
May 17, 2026Michael Arbel, Basile Terver, Jean PonceUnsupervised Learning Visual Representation Learning
Univ. Grenoble Alpes, Inria · CNRS, Grenoble INP, LJK · Ecole Normale Supérieure / PSL +2
Characterizing the visual representation of objects from the child's view
May 14, 2026Jane Yang, Tarun Sepuri, Alvin Wei Ming Tan +3Representation Learning Visual Representation Learning
Department of Psychology, University of California San Diego · Department of Psychology, Stanford University · Department of Computer Science, Stanford University
Rethinking the Good Enough Embedding for Easy Few-Shot Learning
May 13, 2026Michael Karnes, Alper YilmazVisual Representation Learning Few-Shot Learning
The Ohio State University, Columbus, OH 43210, USA
Characterizing Universal Object Representations Across Vision Models
May 13, 2026Florian P. Mahner, Johannes Roth, Ka Chun Lam +3Visual Representation Learning Representation Alignment
Vision and Computational Cognition Group Max Planck Institute Justus-Liebig-University Giessen · Machine Learning Core National Institute of Mental Health Bethesda, MD, USA · Department of Cognitive Science Johns Hopkins University Baltimore, MD, USA
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
May 12, 2026Alan Z. Song, Yinjie Chen, Mu Nan +3Visual Representation Learning Vision Transformer
Carnegie Mellon University · University of Hong Kong
WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
May 12, 2026SeongMin Jin, Doo Seok JeongRepresentation Learning Visual Representation Learning
1Division of Materials Science and Engineering · Department of Semiconductor Engineering
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
May 12, 2026Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet +3Cross-View Geo-Localization Visual Representation Learning
Faculty of Information Technology, University of Science, Vietnam National University, Ho Chi Minh City, Vietnam. · Department of Computer Science, University of Warwick, Coventry, United Kingdom.
FeatMap: Understanding image manipulation in the feature space and its implications for feature space geometry
May 11, 2026Elias B. Krey, Nils Neukirch, Nils StrodthoffNeural Representation Geometry Visual Representation Learning
Division AI4Health Carl von Ossietzky Universität Oldenburg Oldenburg, Germany
Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
May 11, 2026Shijie Wang, Yadan Luo, Zijian Wang +2Visual Representation Learning Fine-Grained Image Retrieval
The University of Queensland, Australia · The University of Adelaide, Australia
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
May 10, 2026Katarzyna Filus, Kamil Faber, Roberto Corizzo +1Visual Representation Learning Continual Learning
Institute of Theoretical and Applied Informatics Polish Academy of Sciences, Gliwice, Poland · AGH University of Krakow Krakow, Poland · American University Washington DC, USA +1
SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations
May 10, 2026Mario Edoardo Pandolfo, Enrico Grimaldi, Lorenzo Marinucci +4Neural Representation Geometry Visual Representation Learning
Dept. Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy. · National Inter-University Consortium for Telecommunications (CNIT), Parma, Italy. · Dept. of Statistical Sciences, Sapienza University of Rome, Rome, Italy. +1
3D MRI Image Pretraining via Controllable 2D Slice Navigation Task
May 7, 2026Yu Wang, Qingchao ChenVisual Representation Learning Self-Supervised Pre-Training
Beijing University of Posts and Telecommunications · Peking University
Look Beyond Saliency: Low-Attention Guided Dual Encoding for Video Semantic Search
May 7, 2026Faisal Aljehrai, Mohammed A. Alkhrashi, Alreem Almuhrij +6Visual Representation Learning Information Retrieval
Saudi Data And Artificial Intelligence Authority (SDAIA)
CRISP: Compositional Relations as Invariant Structural Priors for Domain Generalization
May 7, 2026Dat Nguyen, Duc-Duy NguyenRepresentation Learning Visual Representation Learning
Harvard University Basis Research Institute · Hanoi University of Science and Technology
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
May 7, 2026Panqi Yang, Haodong Jing, Jiahao Chao +5Visual Representation Learning Image Tokenization
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence,National Engineering Research Center of Visual Information and Applications,and Institute of Artificial Intelligence and Robotics, Xi’an Jiao Tong University · Xiaohongshu Inc.
Extremely coarse learning objectives induce human-aligned representations in AI vision models
May 7, 2026Yash Mehta, Michael F. BonnerVisual Representation Learning Fine-Grained Image Classification
Department of Cognitive Science, Johns Hopkins University
Exploring Clustering Capability of Inpainting Model Embeddings for Pattern-based Individual Identification
May 6, 2026Jens van Bijsterveld, Daniele Avitabile, Fons J. Verbeek +1Biometric Identification Visual Representation Learning
Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands · Naturalis Biodiversity Center, Leiden, The Netherlands · 1Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands +2

May 28, 2026, cs.ROJ/K move · Enter open · S save

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

Jusuk Lee, Seungjae Lee, Jonghun Shin, Hoseong Jung+5

Seoul National University · University of Maryland, College Park · Georgia Institute of Technology

Cross-Modal Learning Cross-Modal Representation Learning Visual Representation Learning Multimodal Pretraining Generalization in Robotic Manipulation Robotic Manipulation+1

Open paper AskPDF arXiv

Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recognition or vision-language alignment, leaving motion understanding to downstream policies. We introduce DynaFLIP, a dynamics-aware multimodal pre-training framework that pushes motion understanding upstream into perception. We construct image-language-3D flow triplets from heterogeneous human and robot videos, and use these triplets as training-time supervision to shape an image-only encoder. Our key idea is to encourage the three modalities to span a small simplex volume in the shared hyperspherical space -- a smaller simplex volume indicating stronger alignment. To avoid the geometric ambiguity and trivial collapse of naive volume minimization, we combine simplex-volume minimization with a cosine regularizer and a contrastive objective. Our analyses show that DynaFLIP focuses on control-relevant regions critical for manipulation. The resulting dynamics-aware representations serve as reusable visual backbones and consistently outperform baselines across diverse downstream policies, including VLAs. We validate this across diverse simulation and real-world setups, with gains reaching +22.5% under out-of-distribution scenarios. Our results suggest that robot generalization improves when visual representations are trained to encode not just what is present, but how the world changes under action.

Momentum

Related topics

Latest papers 147