Computer Vision news and analysis on Web Pulse: 4320 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers proposed FRPSS (Feature Rearrangement in Pre-Shape Space), a single-image generation method whose core MSR-FAGS module replaces randomly initialized low-scale generator features with rearranged Pre-Shape feat…
A new parameter-pruning scheme derived from the Fisher information metric's geodesic distance in model space outperforms magnitude pruning and local Fisher information pruning across every architecture and dataset combin…
A new training framework for Visual Question Answering (VQA) achieves 61.64% accuracy on the bias-sensitive VQA-CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, a generalization gap of 1.16%, acco…
Researchers introduced MechReason, a benchmark of 12,000 question-answer pairs and 21,000 visual materials drawn from real mechanical engineering papers, to test multi-image, multi-hop reasoning in multimodal large langu…
A new adaptive diffusion controller dynamically adjusts the number of denoising steps in text-to-image diffusion models based on input prompt complexity, reducing inference time while maintaining visual fidelity without …
Apple announced Apple Reference Image, an opt-in camera mode debuting on the main camera sensor of iPhone 18 Pro and iPhone 18 Pro Max that creates securely timestamped reference images reflecting what the iPhone's camer…
Skydio posted a Senior Autonomy Engineer - Computer Vision role in San Mateo, California, with an annual base salary range of $170,000 to $277,500. The listing, filed under Core ML roles, sits 6% below the $238,000 media…
Researchers at UCL developed an AI tool that predicted from 11,089 MRI scans of more than 8,500 patients across the UK, US, Netherlands and Nigeria whether brain tumours would brighten on contrast-enhanced scans, correct…
A three-stage pipeline built on Stable Diffusion 1.5 can generate synthetic leprosy lesion images by transferring texture from general chronic wound photography, according to a paper (arXiv:2609.13226v1). The researchers…
Artist-built app Foxglove, released free on the App Store at version 1.0 (Build 5) and now at 1.1 (Build 7), strips EXIF/GPS metadata, embeds a steganographic ownership watermark, and applies adversarial perturbation to …
Adafruit published a new Learn Guide for Pico-Faces, an image generation model that runs on a microcontroller and implements a latent flow diffusion transformer (DiT). The project targets microcontrollers capable of runn…
ASRock Industrial introduced a lineup of industrial edge AI platforms built on Intel Core Ultra Series 3 processors (Panther Lake-H), offering up to 180 platform TOPS and support for up to 128 GB of DDR5 memory at speeds…
Lexius, a San Francisco startup founded by David Elskamp and Liam Webster and listed in Y Combinator's Winter 2026 batch, has narrowed its camera-AI pitch to checkout loss software that matches existing store cameras aga…
MYWAI has ported its VILMA (Visual Imitation Learning for Manipulation Activities) Toolkit to Arduino UNO Q and VENTUNO Q boards powered by Qualcomm Dragonwing processors, letting robots learn manipulation tasks from a s…
Researchers introduced E2A-Bench, a new benchmark for measuring evidence-to-action reliability in financial chart reasoning by vision-language models (VLMs). The benchmark targets a gap in existing hallucination evaluati…
Pakistan Telecommunication Company Limited (PTCL) will deploy SILA, an AI-powered sign language agent built by Pakistani accessibility technology company ConnectHear, across its customer care centers beginning in Karachi…
Axelera AI is shipping Europa, its second-generation AI Processing Unit (AIPU), which delivers 629 TOPS at INT4, INT8, or INT16 within a 45W TDP from eight second-generation AI processing cores, the Eindhoven company sai…
Dynin-Robotics has implemented an omnimodal unified diffusion vision-language-action model that brings visual goal and dynamics prediction into action generation and selection through a shared trajectory model, according…
LynnReal-Omni was introduced as a native multi-modal video generation model designed for agentic visual workflows, addressing the stochasticity and control problems of video diffusion models. The model targets precise co…
InclusionAI released Ling-3.0-flash-VL, a hybrid instant/reasoning model with tool calling that builds on Ling 3.0 Flash (124B total / 5.5B active MoE) and adds native visual perception and advanced visual agent capabili…