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 40
Measuring What Matters: A Causal Reliance Score for Histopathology Image Segmentation
Reliable histopathology segmentation requires models that rely on pathology-relevant structures rather than spurious background correlations.WorkIng: A Real-World and Synthetic Highway Work-Zone Benchmark Dataset for Autonomous Navigation
Highway work zones are critical edge cases for autonomous vehicles (AVs), combining atypical geometries and jurisdiction-specific regulations that existing benchmarks fail to capture: real-world…Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition
Multi-head attention in Vision Transformers (ViTs) allows independent attention patterns across heads, but without explicit regularization, heads may learn redundant patterns rather than…Different Models, Shared Failures: Auditing Frozen-Encoder Pools for Medical Segmentation
Average segmentation accuracy and model count do not reveal whether models fail on the same cases.A Patch is More Than a Token
Vision Transformers represent each image patch through a canonical token produced under one observation condition.PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization
Camera localization methods are mostly multi-stage pipelines relying on dedicated and complex maps that are costly to construct, store, and maintain over time.ObjectGuidedMap: An Object-Aware Model for Robust Bird's Eye View Map Prediction in High-Occlusion Scenarios
Accurate BEV map prediction is a critical component of autonomous driving systems, enabling downstream planning and control.ReuScope: Auditing Data Reuse and Evaluation Sensitivity in Capsule Vision 2024
We develop ReuScope, a protocol for auditing data reuse and evaluation sensitivity, using Capsule Vision 2024 as a case study.Open-Weight MLLMs Cannot Compare What They Cannot Name
Multimodal Large Language Models (MLLMs) are increasingly capable of understanding images and performing complex visual reasoning, suggesting the possibility of using them to automate biological…Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos
Scaling humanoid motion foundation models is constrained by the scarcity of diverse, robot-executable data and by the difficulty of jointly learning from heterogeneous multimodal inputs while…IGDA-ICMH: an Importance Guided Feature and Network Dual Adaptation Framework towards Image Compression for Machine and Human Vision
With the surge of machine vision applications, image compression for both machine and human vision (ICMH) has become an important research area.TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs
High accuracy on streaming video benchmarks does not establish whether a model uses visual history.FoAViS: Analyzing Learned Fixation Strategies in a Foveated Active Vision System
Human vision is foveated and active: resolution is highest at the fovea and falls off towards the periphery, and fixations are actively directed to locations of interest.MoETok: Sparse Expert Routing for 1D Visual Tokenizers
Modern visual tokenizers aim to preserve fine-grained visual details while learning high-level semantic representations for downstream generation and understanding.GeoFlip Preview: Benchmarking Geometry-Sensitive Physics in Video Generation
Video generation models synthesize realistic motion, but can they respond correctly to changes in initial geometry?Any Forcing: Any-Step Generality and One-Step Stability for Autoregressive Video Generation
Autoregressive video generation enables efficient inference through streaming prediction.Learning Clean Generative Processes from Noisy Measurements
We study how to learn a generative model of clean images using only noisy observations.REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control
Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to serve as fine-grained controllers.Think in 360°: Benchmarking and Bootstrapping Panoramic Video Reasoning
A panoramic video captures all directions around the camera, but relevant evidence can appear in different directions and at different times.Rethinking Asymmetry in Self-Supervised 3D Geometry Learning
Self-supervised learning relies on asymmetry between what a model observes and what it must explain.