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

CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations
Sep 8, 2026Aman Mehta, Riya BaviskarPhysical Reasoning Visual Representation Learning
Independent Researcher
GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation
Sep 3, 2026Yupeng Zheng, Xiang Li, Songen Gu +11Visual Representation Learning World Models for Robotics
Institute of Automation, Chinese Academy of Sciences · Tsinghua University · Fudan University +2
Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications
Sep 1, 2026S. Sifaoui, E. Angelini, S. Toupin +2Representation Learning Visual Representation Learning
LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France · MIRACL.ai Laboratory, Hôpital Universitaire Lariboisière (AP-HP), Paris, France · Université Paris Cité, Inserm MASCOT, Paris, France
On the Design Fundamentals of Pixel Text Representation Learning
Sep 1, 2026Chaohao Yuan, Ruifeng Yuan, Zhuoxu Huang +4Visual Representation Learning Vision-Language Alignment
1The Chinese University of Hong Kong · 2DAMO Academy, Alibaba Group · 3Fudan University +4
Vision Models Predict Urban Scene Appraisal with Limited Neural Alignment
Aug 31, 2026Kaizhen Tan, Yuantao DengRepresentational Similarity Analysis Neural Representation Geometry
New York University
DINOcular: Self-Supervised Visuospatial Representations
Aug 27, 2026Farkhat Almukhamedov, Sami Azirar, Hermann BlumVisual Representation Learning Geometric Representation Learning
Robot Perception and Learning Lab University of Bonn & Lamarr Institute
DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models
Aug 24, 2026Jeong-gi Kwak, Sho Kagami, Yuki Ono +1Multi-View Consistency Visual Representation Learning
University of British Columbia · Sony Semiconductor Solutions Corporation · Sony Corporation
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
Aug 9, 2026Jinbo Yan, Limeng Qiao, Jie Qin +3Visual Representation Learning Unified Multimodal Models
Meituan
Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Controlled Interventions
Aug 6, 2026Zhongyao Wang, Wanli Ouyang, Taoyong Cui +1Visual Representation Learning Representation Disentanglement
Fudan University · MMLab, The Chinese University of Hong Kong · Department of Computer Science and Engineering, The Chinese University of Hong Kong
Learning visual representations for compositional analysis of artworks and photographs
Aug 6, 2026Fatemeh Behrad, Tinne Tuytelaars, Johan WagemansVisual Representation Learning Compositional Representation Learning
KU Leuven University Belgium
IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers
Aug 5, 2026Vaishnavi B Mohan, Vijayakrishna Naganoor, Yashas Annadani +1Transformer Interpretability Visual Representation Learning
University of Washington, USA · Microsoft, USA · TU Munich, Germany +1
VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval
Aug 2, 2026Haocheng Wang, Tongkun Guan, Wei Shen +1Visual Representation Learning Late Interaction Retrieval
MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University, China
Foveated Probes Recover Localized Binding Information in Vision Foundation Models
Aug 1, 2026Mateusz Michalkiewicz, Mahsa Baktashmotlagh, Guha BalakrishnanVisual Representation Learning Vision Foundation Models
Rice University, Houston, TX, USA · The University of Queensland, Brisbane, QLD, Australia
Artificial Intelligence for the Characterization of Particles and Fibers by Optical Microscopy
Aug 1, 2026Simiao Sun, Kenneth Ng, Lynn Lee +6Cross-Modal Knowledge Distillation Visual Representation Learning
Department of Chemistry, University of Hong Kong, Hong Kong SAR · Museum Studies Program, University of Hong Kong, Hong Kong SAR · Department of History, City University, Hong Kong, Hong Kong SAR +3
RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning
Jul 31, 2026Qian Wang, Longrui Chen, Peiran Sun +8Visual Representation Learning Robot Skill Learning
Karlsruhe Institute of Technology, Germany · University of Leeds, United Kingdom
Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
Jul 31, 2026Alexandros Haridis, Charles ZhouVisual Representation Learning
Harvard University, Cambridge, MA 02139, USA
Logographic Character Visual Pretraining via Semantic-based Contrastive Learning
Jul 30, 2026Daqian Shi, Wei Cao, Xiaoyu Zheng +3Contrastive Learning Visual Representation Learning
Queen Mary University of London London, UK · Jilin University Changchun, China · King’s College London London, UK +1
Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training
Jul 22, 2026Qiwei Ma, Bin Deng, Junjie Zhu +5Visual Representation Learning Self-Supervised Pre-Training
School of Artificial Intelligence and Robotics, Hunan University, Changsha, 410082, Hunan, China · Intelligent Game and Decision Lab, Beijing, 100166, Beijing, China · Yuelushan Center for Industrial Innovation, Changsha, 410082, Hunan, China
Spiking Neural Networks for fMRI-Based Visual Semantic Decoding
Jul 21, 2026Jiahong Zhang, Jinning Zhao, Sijun Shen +3Visual Representation Learning Neural Decoding
Institute of Automation, Chinese Academy of Sciences, Beijing 100045, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China
scMIR: a vision-language foundation model for single-cell light microscopy image representation
Jul 21, 2026Yifan Shang, Jiahui Tan, Xiangxiang Zeng +1Cross-Modal Representation Learning Visual Representation Learning
Laser Metrology and Biomedicine Lab, Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong, China · State Key Laboratory of Chemo and Biosensing, College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
Jul 21, 2026Jin Yu, Juyoun ParkVisual Representation Learning Visual SSMs
Center for Humanoid Research Korea Institute of Science and Technology
Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures
Jul 19, 2026Gautam Ranka, Paras ChopraVisual Representation Learning
Lossfunk
Beyond Color Geometry: Evaluating Human-Like Color Representations in Vision Models
Jul 15, 2026Ayan Igali, Pakizar ShamoiVisual Representation Learning Fine-Grained Visual Perception
School of Information Technology and Engineering Kazakh–British Technical University Almaty, Kazakhstan
TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts
Jul 10, 2026Anguelos Nicolaou, Antonella Ambrosio, Desiree Di Donato +1Visual Representation Learning Authorship Attribution
University of Graz, Graz, Austria · Università degli Studi di Napoli Federico II, Naples, Italy
Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing
Jul 10, 2026Chenxu Peng, Chongtian zhou, Dicheng Liu +5Event-Based Vision Visual Representation Learning
VCIP, CS, Nankai University · NKIARI, Shenzhen Futian · AAIS, Nankai University
Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
Jul 9, 2026Matthias Tangemann, Benjamin Lo, Zygmunt Pizlo +3Visual Representation Learning Vision Transformer
University of Toronto · 2Vector Institute · 3McGill University +2
Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
Jul 9, 2026Ludovica de Paolis, Marco Baroni, Alessandro Laio +1Visual Representation Learning Vision Transformer
Department of Neuroscience, International School for Advanced Studies (SISSA), Trieste, Italy · Department of Language and Translation Sciences, Pompeu Fabra University, Barcelona, Spain · ICREA, Barcelona, Spain +1
Unpaired Joint Distribution Modeling via Multi-Scale Image Representations
Jul 9, 2026Yihang Zou, Hui Zhang, Zuowei Shen +1Visual Representation Learning Unsupervised Representation Learning
Yau Mathematical Sciences Center and Department of Mathematical Sciences, Tsinghua University, Beijing, China · Qiuzhen College, Tsinghua University, Beijing, China · Department of Mathematics, National University of Singapore, Singapore +1
VEIL: How Visual Encoding Hijacking Induces Bias In Vision Models
Jul 6, 2026Suranjana Sooraj, Xuyang Chen, Madhumitha Venkatesan +1Scientific Visualization Data Visualization
University of California, Davis
Geometry-aware Depth-guided Representation Learning for Structure-preserving Low-light Image Enhancement
Jul 6, 2026Fang Gao, Jiongkai Qin, Jiabao Wang +5Image Enhancement Visual Representation Learning
School of Electrical Engineering, Guangxi University, Nanning, Guangxi 530004, China · School of Rail Transportation, Soochow University, Suzhou, Jiangsu 215500, China

Sep 8, 2026, cs.ROJ/K move · Enter open · S save

CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations

Aman Mehta, Riya Baviskar

Independent Researcher

Physical Reasoning Visual Representation Learning World Model Evaluation

Open paper AskPDF arXiv

How far a pushed object slides depends on its mass and friction, which no single image reveals. Pretrained visual encoders are increasingly used as the perception front end of world models for manipulation, and their physical competence is assessed with perturbation benchmarks and linear probes, almost always in a clean, fixed-camera scene. We show that these assessments cannot distinguish an encoder that infers physics from one that does not. CALIPER (calibrate, then predict) is a direct test: an object of unknown mass and friction is struck twice at known speeds, a third strike is shown only up to the moment of contact, and a linear readout on frozen features must predict how far the object slides. Swapping in another object's calibration clips checks that the evidence is actually used. Across 2,000 simulated episodes and eight representations, from V-JEPA 2 to a randomly initialised ViT and raw pixels, calibration adds +0.50 R^2 and the swap removes it. Yet in the clean scene every representation lands within 0.02 R^2 of the ceiling set by true simulator state, because a fixed camera exposes the object's displacement directly in pixel coordinates. Resampling camera, lighting, and clutter for every clip spreads the same representations across 0.50 R^2; when the readout chooses a push speed for a goal distance, V-JEPA 2 misses by 4 mm and the random ViT by 20 mm, no better than ignoring the object. Linear probes track none of this: a change in frame aggregation moves a probe more than pretraining does, and erasing the probed mass direction from the same representation costs nothing in one scene and 0.35 R^2 in the other. Whether a benchmark can rank models is an empirical property, and we give three checks that establish it.

Momentum

Related topics

Latest papers 147