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: 4,999 arXiv preprints and 1 OpenAlex record.
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 55
Confident First, Reflective Second: Reinforcement Learning of Confidence-Preserving Reflection for Video Understanding
Video models answer from sampled frames and may miss the decisive moment.Spatial-Frequency Learning for Scanning Transmission Electron Microscopy Image Enhancement
Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution and plays a key role in the discovery and characterization of advanced…GarmentSegAgent: Autonomous Garment Segmentation for Web Fashion Images via Textual Self-Refinement
Web fashion images support applications such as visual product search and consumer-to-shop matching, yet their visual heterogeneity makes reliable garment segmentation challenging.ARISE: Authentic Reference-Informed Stability Enhancement for Continual Multimodal Forgery Detection
Multimodal forgery detection is commonly studied under a static assumption: training attacks are expected to approximate those encountered after deployment.Identity or Evidence? Auditing Evidence Dependence in Agentic Life-Science Benchmarks
Agentic life-science benchmarks give an agent evidence about a named entity and score an answer against a recorded outcome.PRISM: Pathology Reliability In Scarce-label Medicine. A Tile-level Benchmark of Pathology Foundation Models
Pathology foundation models are typically benchmarked on classification performance at full label availability and on in-distribution test sets, while calibration, behavior at low label budgets, and…RoboAuto: Autonomous Robot Program Search through Multi-Level Physical Understanding
Recently, LLM-based autonomous agents have shown strong capabilities in iteratively generating, evaluating, and refining executable solutions.Frugal Handwritten Text Recognition for Sub-Saharan Civil-Status Registers: A Smartphone-to-Records Pipeline with CPU-Only Inference
Handwritten civil-status registers across Sub-Saharan Africa are being photographed, but rarely transcribed, which leaves their content unsearchable.FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation
Unified conditional image generation requires a single model to preserve different aspects of a visual input while producing a target image that follows textual guidance.PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy
Final-answer accuracy reports whether a vision-language model was right, but not whether its answer was grounded in the image, whether its stated reasoning reflects that evidence, or what the answer…Decoupling Consistency and Conflict across MLLM Layers for Fake News Detection
The trustworthiness of Web content faces a growing threat from multimodal fake news.LabWorld: Learning Interactive 4D Worlds for Scientific Experimentation
Autonomous scientific agents must not only reason about experiments but also interact with the physical environments in which they are executed.WithinVAE: Compact Visual Autoencoding with Self-Distilled Semantics
Visual autoencoders must balance reconstruction fidelity, compactness, and semantic structure.Camera-to-Quadruped Robot Pose Estimation from Sequential Images
Quadruped robots are increasingly deployed in hazardous environments such as disaster response and facility inspection, where external-camera monitoring is essential for safe operation.4D Reconstruction with Events & RGB
Reconstructing dynamic 3D scenes over time (4D reconstruction) from a single moving camera is central to robotics and AR/VR applications, yet state-of the-art feed-forward methods rely solely on RGB…Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction
World Action Models (WAMs) leverage pretrained video generative models for robotic control by jointly predicting future visual observations and actions.Image Modeling: From Handcrafted Priors to Foundation Image Models
This paper unifies six decades of image modeling, evolving from handcrafted mathematical tractable priors to solve inverse problems in imaging to data-driven deep foundation image models for both…SAGE: Semantic-Augmented Geometric Experts for Point Cloud Registration
Point cloud registration is an essential task for scene reconstruction, requiring the alignment of partially overlapping point clouds.SWIM: Learning What Matters from Behaviors for JEPA World Models
Joint-embedding predictive architectures (JEPAs) enable world models to plan from images by predicting future embeddings.Haste Makes Waste? Towards Safe Few-Step Text-to-Image Models
While few-step distilled text-to-image models have gained traction due to their fast generation times, the speed-up implications on their unsafe generation rates remain unknown.