Computer Vision

Ant Group's embodied-AI unit Robbyant open-sourced LingBot-Vision, a family of self-supervised Vision Transformers designed for dense spatial perception, on Hugging Face under Apache-2.0. The 1.1B-parameter flagship mode…

Sejong University's Future GPU Research Institute, led by professor Park Woo-chan, is accelerating development of next-generation GPU and AI-semiconductor technologies, focusing on real-time path tracing for applications…

Sejong University's Future GPU Research Institute, led by professor Park Woo-chan, is accelerating development of next-generation GPU and AI semiconductor technologies, focusing on real-time path tracing to overcome nois…

Meta Superintelligence Labs launched Muse Image on July 7, the first image generator that autonomously uses tools like web search and code execution at inference time, with self-refinement emerging from reinforcement lea…

A developer built PostureGuard, a real-time posture monitoring tool using MediaPipe, OpenCV, and Electron. The tool runs on a standard CPU and detects forward head posture via pose estimation, sending alerts through a We…

A new analysis explains how predictive processing shapes the content of visual hallucinations in Charles Bonnet Syndrome, suggesting that learned expectations sculpt bursts of neural activity into persistent hallucinatio…

Florida Crystals Corporation Senior Laboratory Manager Brian Ton explained on the Emerj AI in Business podcast how to move visual AI inspection from pilot to standard practice in complex manufacturing, emphasizing valida…

AMD Silo AI and the Autoware Foundation are using GPU partitioning on AMD Instinct MI300X accelerators to accelerate hyperparameter optimization for autonomous driving perception models, enabling up to 64 parallel traini…

Meta announced an update to its smart glasses that will disable the camera if the privacy LED light is tampered with or destroyed, following public backlash and reports of modders physically drilling into the light. The …

Meta's AI glasses, used by millions daily for hands-free photos, video, and AI assistance, feature a blinking white LED that signals when content is being captured. The company has implemented safeguards that disable the…

Meta Superintelligence Labs released Muse Image and Muse Video, its first media generation models. Muse Image offers advanced image generation with agentic tool use, while Muse Video provides high-fidelity video with nat…

Meta released a web-based detection tool that identifies images and videos created with its new Muse Image model by checking for invisible Content Seal watermarks, which persist even after cropping or screenshots. The to…

Researchers at Goodfire, Harvard, Stanford, and Brown introduced Block-Sparse Featurizers (BSF), a method that decomposes neural network activations into multidimensional subspaces instead of single directions. Applied t…

Meta's Muse Image model rose to second place on Arena.ai's Text-to-Image Arena leaderboard with an Elo score of 1280, trailing only OpenAI's GPT Image 2 at 1385. The model, announced by Meta Superintelligence Labs, featu…

A developer launched AutoSprite, an AI-powered spritesheet generator that lets game developers upload or create characters and automatically generate aligned animations for idle, walk, run, jump, attack, or custom moves …

Meta launched Muse Image, a free AI image generator developed by Meta Superintelligence Labs, available on Meta AI app, Instagram Stories, and WhatsApp. The tool offers presets, prompt-based editing, and integration with…

OCR Buddy, a free and open-source Chrome extension, provides fully local OCR for code, formulas, and tables using PaddleOCR's PP-OCRv5 on ONNX Runtime Web, ensuring no data leaves the user's machine and eliminating hallu…

Paul Hawkins created Hawk-Eye in 2001, and the Sony-owned optical tracking system now powers VAR, tennis line calls, and goal-line reviews across more than 25 sports in 43 countries. The system uses calibrated multi-came…

Meta launched Muse Image, its first image model from Meta Superintelligence Labs, and a comparison of its text-to-image prompts against Nano Banana Pro, GPT Image 2, and FLUX 2 Pro shows that while Muse excels at persona…

Meta launched Muse Image, its first AI image model from Meta Superintelligence Labs, now available in the US through Meta AI, Instagram, and WhatsApp. The model generates and edits images from complex prompts, integrates…