Computer Vision news and analysis on Web Pulse: 1814 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers at Fourthline, a KYC identity verification company, observed that AI models trained with supervised versus contrastive loss functions produce different prediction scores when the input video codec is changed.…
A comprehensive guide has been published covering the history, techniques, datasets, algorithms, tools, and real-world applications of image reconstruction using deep learning. The resource details how deep learning mode…
Niantic Spatial, an AI company spun out of Pokémon Go developer Niantic in May 2025, used billions of real-world images captured by millions of Pokémon Go players to train a "large geospatial model" for navigation techno…
Maneva raised $27-million USD in Series A funding to expand its AI vision technology for manufacturing, with plans to scale into North America and enter Asian markets.
A developer has built a CPU-only voice agent that replicates four key behaviors from Thinking Machines' 276B-parameter Interaction Models demo using off-the-shelf parts and commodity AI models on a single laptop. The pro…
Zyphra released Zamba2-VL, a family of open vision-language models in 1.2B, 2.7B, and 7B parameter sizes, built on a hybrid Mamba2–Transformer backbone. The models achieve competitive accuracy on benchmarks including doc…
Seoul's municipal government will deploy artificial intelligence to monitor expressways and crowded stadiums across the city. The AI network aims to improve public safety and traffic management by analyzing real-time foo…
Thousands of Indian homemakers and factory workers are recording first-person video of everyday tasks such as cooking and folding clothes using head-mounted cameras and motion sensors, with pay reported at about Rs 250 p…
The Seoul Facilities Corporation will deploy AI-powered safety systems across the capital's expressways, stadiums, and public grounds this year, replacing manual surveillance with automated hazard detection. The initiati…
NEURA Robotics closed a $1.4 billion Series C, the largest full-stack robotics funding round in history, as the race to control the Physical AI ecosystem intensifies. Sharpa integrated its Wave tactile gloves into the Un…
Indian housewife Nagireddy Sriramyachandra films herself slicing mangoes with a smartphone strapped to her head, earning just over two dollars an hour to train AI-powered robots for future household tasks. She is one of …
MONAI, an open-source medical imaging framework, has released a tutorial demonstrating an end-to-end 3D spleen segmentation pipeline using a UNet model on CT volumes from the Medical Segmentation Decathlon Task09 dataset…
Miniaturization, AI voice interaction, and multimodal video input are converging to drive major tech companies toward all-day AI glasses with cameras, sparking immediate public backlash. Meta, Google, Samsung, Apple, Ama…
A high school in Seoul's Seodaemun District demonstrated AI-powered surveillance technology on Wednesday that detects fights in real time and alerts administrators to intervene immediately. The system, which flags unusua…
Ukrainian forces are deploying waves of AI-guided drones to strike Russian supply lines in occupied Ukraine, with upgraded medium-range models featuring autonomous targeting and greater resistance to electronic jamming. …
Ukraine launched a "Logistics Lockdown" campaign using AI-guided Hornet kamikaze drones, developed by US company Swift Beat LLC with backing from former Google CEO Eric Schmidt, to strike Russian fuel tankers, convoys, a…
Avataar AI, a startup selected for India's $1.2 billion India AI Mission, launched a new video generation model called Varya that is 10 times faster and 20 times cheaper than competitors like Veo and Runway. The model, b…
Researchers introduced GRIP, a feedback-guided retrieval framework for multimodal in-context learning that selects examples based on their actual impact on model predictions rather than visual similarity. The system impr…
Researchers have developed CD-RCM, the first novel-view synthesis approach specifically for reflectance confocal microscopy (RCM), enabling continuous-depth visualization of human skin from sparse, anisotropic z-stacks. …
Researchers have developed L-VARC, a novel framework that enhances visual reasoning on the Abstraction and Reasoning Corpus (ARC) by integrating a language-guided Learning Using Privileged Information (LUPI) branch. The …