Computer vision
Machines that see: detection, recognition, OCR, segmentation and vision-language models
Latest stories See all →
- Multimodal AI for Developers: Build AI That Can See, Hear, Speak & Create
- How Retailers Are Using AI to Measure In-Store Shopper Behavior
- AIR-055: Compact Multimodal Vision AI System Powered by Qualcomm Dragonwing IQ9
- Canny Edge Detection in Computer Vision
- 6 AI-powered audience segmentation tools worth evaluating in 2026
- How Does AI Image Detection Work?
- Moonshot AI Launches Kimi K2.8 Preview Multimodal Model
- AI Image Generator for DND: 10 Tools Compared
- The best AI photo editors in 2026
- Apache Doris 5.0 Variant Across Internal and Open Lakehouse Tables
- jina-ocr-v1: Faster Document Parsing on Low-Budget GPUs jina-ocr-v1 is a vision language model with 3.4B parameters and 570M active parameters, scoring 91.1 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench.
- Moonshot AI Launches Kimi K2.8 Preview Multimodal Model
- GPT Image 2.5 vs Nano Banana 2: which one fits your brief?
- GPT Image 2.5 prompting guide: 12 prompts for precise edits
- Generate images with Pydantic AI
- Best AI Image Generator in 2026: 8 Tools Compared
- DeepSeek-V4.1-Flash Packs 552B Parameters With Efficient MoE Inference
- The Best AI Photo Enhancers in 2026: Fix Blurry, Low-Res, and Old Photos (6 Tools Compared)
- BISIDI Introduces a Chat-Based AI Image Editor for Architecture, Interior Design and E-Commerce
- How I Use Claude and ChatGPT to Make Better AI Images
- Did Anthropic Secretly Nerf Claude Code? The Real Timeline
- Just-in-Time Agentic OCR
- ChatGPT Images 2.5 Launches with Personalized Visuals
- AI Image Generator for Beginners Made Simple with Starryai
Podcasts
Recent episodes
- Episode 416: Steam Frame Reviews Hit, Pop OS/Cosmic Testing & More
- How Physical AI Learns Across Language, Video and Action — Ming-Yu Liu
- Closing the Gap Between Commercial Plans and What Happens on the Shelf - with Stephanie Lilley of Reckitt
- Finding Potholes Before They Form With AI and Univrses
- OpenAI Cuts Off Cursor, Nvidia Buys Hugging Face, Ox Alpha is GLM | This Week In AI
- IM 885: Get on the Butter Box - Can Local AI Models Outperform Frontier Labs?
- Pixel 11 gets in on the digicam trend
- Running Enterprise Computer Vision on CPUs With Ultralytics YOLO26
- 🔬 The Lab of the Future Should Feel Like a Data Center — Andy Beam & Rafa Gómez-Bombarelli, Lila Sciences
- James Rendell: Why Your Cat Model Is Blind to Secondary Perils | TRP #175
- Property Intelligence at Scale: How Geospatial Data Is Redefining Insurance Underwriting | Izik Lavy and Jacob Grob
- Off The Hook - Wed, 24 Jun 2026 19:00:00 EST