Computer Vision news and analysis on Web Pulse: 4298 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
A developer released a free native macOS image editor built with Swift and Rust that includes an optional AI agent harness allowing a model to remote-control the application to build documents from layers, effects, and b…
A developer building the AI photo app CMeIn added a pre-generation gate that checks uploaded photos against five facial poses — straight on, turned left, turned right, and both profiles — and requires at least two to be …
A developer built TraiLens, an offline-first Python tool that generates a Markdown nature journal from hiking photos using the open-weight Moondream vision model run locally via Ollama. The script loops through a local i…
A developer built TouchQuest, an open-source AI-powered outdoor photography game that uses fixed-timer missions and on-device image verification to push players off their screens and outside. The game runs three levels t…
Researchers at the Weizmann Institute of Science developed Brain-IT, an AI system that reconstructs viewed images from fMRI brain scans, training on more than 70,000 images collected from eight subjects and identifying 1…
Overview AI launched the OV Spark and OV Spark Pro AI inspection cameras, available now directly from the company and through its distribution partners. The Spark camera ships with 10 inspection tools mixable in a single…
Mistral released Mistral Large 4 in public preview on October 6, 2026, an open-weight general-purpose multimodal model built on a granular Mixture-of-Experts architecture with 49B active parameters, 1.05T total parameter…
Researchers introduced HLA-WM, a hybrid linear attention architecture for long-horizon video world models that combines softmax attention's full-history KV cache with recurrent linear attention's fixed-size state compres…
Reka released Rho-1, a 19B research-preview model trained from scratch that unifies text, image, and video understanding and generation plus robot action output in a single network, with all modalities sharing one contex…
Researchers at the Weizmann Institute of Science developed Brain-IT, an AI system that reconstructs images a person is viewing from their brain scans and needs only 60 minutes of scan data to adapt to a new person, versu…
A new technique called In-Distribution Forcing targets drifting in autoregressive video diffusion models, where colors and textures shift and motion dynamics decay during long-horizon video generation. Existing approache…
A developer built TrailTalk, a privacy-first walk journal that runs open-weight vision models such as Gemma 3 4B locally through Ollama to identify plants, trees and birds from photos and save sightings to a local SQLite…
A study evaluating twenty deepfake detectors against ten generators released over the past four years found detection accuracy fell from 99.5% to 76% as newer generative models emerged. The research, which also examines …
A developer behind the Image to Anime web workspace describes building a photo-to-anime image tool, arguing that the hard part of an AI image product is the workflow around the model rather than the model itself. The acc…
A developer built Vanam, an offline AI field guide that uses a device's camera, microphone, and GPS to identify birds and plants and generate field notes entirely on-device without uploading user data. The app runs on-de…
A research team released Pyramid-JiT (P-JiT), a decoder-only pixel-space architecture that predicts target images at several resolutions along the DiT trunk, reaching Linum v2's FD-DINOv2 score with 11.3× fewer training …
A developer guide details how to integrate the DeepfakeDetector.ai API into platforms that accept user-uploaded images and video, covering key generation, image and video detection endpoints, asynchronous job handling, a…
Researchers introduced WM-VLM, a method that probes whether vision-language models can solve spatial problems by reasoning with both text and generated visual states rather than through language alone, according to the p…
A developer built TerraPulse AI, an offline-first, open-source nature companion that runs open-weight vision and audio models entirely in the browser via WebAssembly and WebGPU. The app uses BioCLIP-v2.1, MobileNetV4-Out…
An autonomous AI agent named Vesper built Proof of Grass, a single-file web app that scores weather conditions for going outside and uses an on-device CLIP model via Transformers.js to verify user-submitted photos actual…