Computer Vision news and analysis on Web Pulse: 4325 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Meta has started rolling out a new AI model, Muse Spark, to its Meta Ray-Ban Display smart glasses, marking a significant upgrade from the previous voice assistant. The update, which is rolling out gradually this week, b…
A new white paper details how to build a 100Gbps server-grade automated optical inspection (AOI) platform for next-generation semiconductor inspection, addressing bandwidth, scalability, thermal, and system integration c…
Apple has three new smart home products nearly ready to launch, according to a Bloomberg report. The devices include a new Apple TV set-top box and an updated HomePod mini with faster chips for Siri AI, expected as soon …
Vision-language models (VLMs) fail at price estimation because they over-index on surrounding context rather than analyzing material properties, according to a technical analysis. When a necklace was paired with an expen…
A study by researcher Brianne Lee found that six multimodal large language models priced a $2.43 Temu necklace at $19 to $104 depending on the outfit worn in the photo, with the same object valued up to 3.6 times higher …
Greyparrot raised $27 million in Series B funding on July 28, 2026, in a round led by technology investor Omar Mir. The London company plans to expand its AI waste-intelligence systems in North America and Europe, grow i…
Greyparrot.ai Ltd. raised $27 million in Series B funding led by Om Elite Assets Investment to scale its physical AI recycling infrastructure globally. The company's Greyparrot Analyzer uses AI-enabled cameras to identif…
University of Minnesota Twin Cities researchers announced July 24 an AI vision system that estimates a scuba diver's respiration rate from exhaled bubbles captured by an underwater robot. The study, published in The Inte…
Warwickshire's hospital car park now hosts the UK's first AI-enabled smart lamp-posts, called iLamps, from Conflow Power Group (CPG), which can recognize number plates and faces and are pitched as tools to fight crime an…
Snappyit launched an AI-powered product photography platform that generates ghost mannequin images for fashion and jewelry sellers, eliminating the need for studio shoots and post-production editing. The platform, recent…
Samsung revealed details about its Galaxy Smart Glasses, Android XR smart glasses launching in late 2026, which will offload heavy computing to a connected Galaxy smartphone via split computing. Head of Samsung's XR R&D …
Researchers propose CausAdv, a causal framework for detecting adversarial examples in convolutional neural networks (CNNs) by learning causal and non-causal features and quantifying counterfactual information (CI) per fi…
Researchers introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams that jointly learns event recognition, temporal restraint, and pixel-level editing in a single end-to-end model. On the Ego4D…
Researchers introduced KANEx, the first framework leveraging Kolmogorov-Arnold Networks (KANs) to ground Vision-Language Model (VLM) reasoning for medical explainability, achieving a 10% improvement in visual localizatio…
Researchers introduce FogDrive, a multi-modal synthetic driving dataset for autonomous driving under fog, containing 660 scenes (~133k frames) with four synchronized cameras, LiDAR, and radar across three calibrated fog …
Researchers propose DAMamba-UNet3D, a parameter-efficient state-space model U-Net for 3D medical image segmentation that achieves a mean Dice of 0.815 on BraTS 2020 with ~5.3 million parameters, roughly 13 times fewer th…
A new classification-guided large vision-language model (LVLM) framework for visual information extraction (VIE) from documents achieves 86.43% F1-score in zero-shot inference on a real-world bidding dataset with 16 cert…
Researchers show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), achieving an average improvement of 13.29% in defending jailbreak attacks while also redu…
Researchers introduce γ-Bridge, a look-parametric diffusion bridge for SAR despeckling that uses a schedule L(t) connecting noisy observations at L_obs to the clean limit via exact multiplicative Gamma marginals. The met…
Researchers developed the Language-guided Segmentation-assisted Diagnostic Transformer (LSDT) model, which uses zero-shot segmentation and multi-modal slice fusion to classify prostate cancer into four clinically meaning…