AI & Machine Learning · Computer Science & AI
Computer Vision
The newest papers in Computer Vision that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 29 September 2026 to 5 November 2026: 4,996 arXiv preprints and 4 OpenAlex records.
Get the few papers worth your time in Computer Vision every morning.
Follow Computer Vision and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 210
Localization Lens for Improving Medical Vision-Language Models
Medical Vision-Language Models (Med-VLMs) have demonstrated strong capabilities in clinical tasks.EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning
Vision-language models (VLMs) are increasingly evaluated for egocentric and cross-view video reasoning, yet existing benchmarks largely focus on semantic event understanding, temporal relations, or…TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons
Text-driven motion editing modifies an existing motion sequence according to a text instruction while preserving the content of the source motion.FASTER: Fast Adjoint Stochastic Transport for Endpoint Refinement in Reward-Guided Image Editing
Reward-guided image editing at test time seeks to improve a specified reward while preserving source content and visual plausibility.Cross-Modal Solar Image Synthesis: Adapting the Surya Foundation Model from He I 10830 Å to EUV Translation and Coronal Hole Segmentation
The long observational record of He I 10830 Å offers a means to investigate solar morphology before modern extreme-ultraviolet (EUV) imaging.EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder
Recovering detailed geometry from high-resolution images is critical for precise perception of the surroundings and objects.Frozen in a Frame: The Velocity Blind Spot in JEPA World Models
Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next frame's embedding, always from a single rendered…WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI-Ultrasound Learning
Magnetic Resonance Imaging (MRI) is widely regarded as the optimal sensor for fetal brain analysis due to its superior soft-tissue contrast and anatomical detail.Organize Primitives into Semantic Parts: Reinforcement Reasoning for 3D Segmentation
Primitive-based 3D segmentation offers a compact and explicit alternative to dense surface prediction, naturally supporting structural abstraction and boundary localization.ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and…Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance
We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic scene reconstruction from only six cameras with…ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies
Robots need to anticipate how their actions will change the world, since manipulation success hinges on the resulting contacts and object motions.PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training
A vision--language--action (VLA) policy can complete complex tasks while ignoring the evidence that should determine its actions.Task-Sensitive Geometry of Representation Transfer for Object Detection under Image Degradation
Object detection under image degradation can benefit from clean-image supervision, but aggregate gains do not imply that transferred representation changes are uniformly useful.FLASHSWIN: Unlocking Large Windows and Dense Tokens in Swin Vision Transformers with Memory Efficient Attention
High-resolution vision backbones have long been forced to trade away local token density to afford larger receptive fields.COMPASS: Comet Object Measurement Pipeline with Automated Selection and Scoring
The single-cell gel electrophoresis ('comet') assay is a widely used technique for quantifying DNA damage at the individual cell level.Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation
Federated learning enables medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains challenging.Learning Discriminative Geometry for Drifting Models
Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation.Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models
Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial domains.NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at…