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 7
EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling
Modern video models possess strong visual priors, yet do not natively represent human action in metric 3D space.Where and Why is Grounded Reasoning Useful?
Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual reasoning problems.Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI
Scientific figures give research ideas a visual form through choices of abstraction, composition, and emphasis.ME^2FDiff: Multiscale Expert Enhancing Feature Diffusion in Residual Network for Brain Tumor Segmentation
Automated segmentation of post-treatment glioma from MRI is essential for accurate diagnosis and treatment planning, yet remains difficult.WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark
Holistic perception for autonomous agents requires reliably segmenting and associating scene elements across time and camera views, including objects outside a fixed semantic taxonomy.GREP: Grounding Generated Room Evaluation in Principles
Recent LLM-centric advances can generate attractive furnished rooms by selecting and arranging assets.ReTailor: A Residual Feature Tailoring Framework for Real-Time Cross-Sensor Pansharpening Adaptation
Recent pansharpening models achieve strong fusion performance on trained sensors, yet often generalize poorly to unseen sensors.DualCast: Dual-Image Conditioned Diffusion Transformers for Digital Human E-Commerce Video Generation
Digital human e-commerce video generation requires preserving product appearance, human identity, and overall video style during dynamic demonstrations.Dual Flow: Joint Image-Measurement Flow for Inverse Problems
Existing generative model-based approaches to linear inverse problems typically use the acquired noisy measurement to condition or guide sampling in the image domain.Time-to-Goal: Learned Temporal Metrics for Long-Horizon Planning with JEPA World Models
Joint-Embedding Predictive Architectures (JEPAs) support planning by comparing predicted latent states with an encoded goal.Risk Control Certifies Rates, Not Magnitudes: An Audit of Selective Fetal Biometry
Prenatal ultrasound biometry must return a head circumference (HC) and refuse when the image cannot support one.Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet
Various land-use models characterize land-use patterns and facilitate scenario planning.Feature Puzzles: Single-Image Supervision for Multi-View 3D-Aware Segmentation
Humans can easily recognize the same objects across different viewpoints of a 3D scene, whereas teaching models such multi-view-consistent perception typically requires videos or calibrated…Chronos: Sequential Identity-Preserving Video Generation by Temporal Anchoring
Identity-preserving video generation aims to synthesize high-quality and visually realistic videos from textual and visual conditions while faithfully maintaining the subject's identity across…Do Saliency Maps Fail Dense Breasts? A Chance-Normalized, Confounder-Aware Audit of Explanation Fairness in Mammography
Saliency maps, offered as evidence that mammography classifiers use the cancer, are untested in dense breasts, which can hide cancers.DecoupAttn: Decoupled Sparse Attention for Training-Free Acceleration of Video Diffusion
Sparse attention accelerates few-step video diffusion transformers by computing a few key blocks exactly and compensating for the rest.3D Banff Glomerulitis Scoring for Kidney Transplant Pathology: Feasibility Study for Volumetric Quantification
Quantifying glomerular inflammation in kidney-transplant biopsies is traditionally performed on single whole-slide sections using the Banff "most-severe section" rule, despite the inherently…Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
Mixture-of-Experts (MoE) enables multimodal large language models (MLLMs) to scale capacity efficiently, but expert parameters dominate memory even though only a few experts are activated per token…FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems
Flow matching models have emerged as a dominant paradigm for generative posterior sampling in imaging inverse problems.CLEAR: Color-Texture Latent Alignment for Single Image Reflection Removal
Single Image Reflection Removal (SIRR) seeks to recover the transmitted scene from a photograph captured through glass.