Computer Vision - News Articles

Mingrui Li and Shuhong Liu Claim SGS-SLAM Is First Semantic Gaussian SLAM

Oct 21, 2026

GitHub

Mingrui Li, Shuhong Liu and co-authors release SGS-SLAM, which they describe as the first semantic visual SLAM system built on 3D Gaussian Splatting. The BSD-3-Clause code combines appearance, geometry and semantic features, and targets real-time rendering on Replica and ScanNet scenes.

Research Computer Vision

Datalab Says Indra OCR 1.1 Reads Handwriting and 80+ Languages on CPU

Oct 19, 2026

Datalab

Datalab releases Indra OCR 1.1, a 1M-parameter model that reads handwriting, OCRs 80+ languages and straightens pages tilted up to 45 degrees, all on CPU. Datalab reports an OmniParseBench headline of 66.7, up from 62.3, and 71.4 with --math, with handwriting tests rising from 8.3% to 25.2%.

Foundation Models Computer Vision

Elorian Releases Glimpse, Says Model Beats GPT-6 Astra on Chart Reasoning

Oct 16, 2026

TechCrunch

Elorian released Glimpse, its first AI model, as a research preview with API access; the chat interface is waitlist-only. The Palo Alto startup says the model revisits images mid-reasoning and outperforms GPT-6 Astra on chart reasoning. Pricing runs $0.60 per million input tokens and $3 per million output.

Foundation Models Computer Vision

GPT 6 Astra Scores 53.6 on Elorian Benchmark, Humans Hit 93.1

Oct 14, 2026

substack.com

Elorian and Scale AI release Humanity's Sixth Sense, a 522-question visual reasoning benchmark, where GPT 6 Astra scores 53.6 pass@1 against a human 93.1. Reflection says its Beam model, 501 billion parameters with 23 billion active, trails Chinese open weight rivals on benchmarks.

Foundation Models Computer Vision Open Source

Scale Labs Benchmark Shows GPT-6-astra Scoring 53.6% on Intuitive Visual Reasoning, Humans 93.1%

Oct 08, 2026

Scale Labs

Scale Labs introduces Humanity's Sixth Sense (HSS), a benchmark of image and video items testing intuitive visual reasoning across temporal, spatial, social and abstract structure. Human participants reach 93.1% accuracy, while the top model, GPT-6-astra, scores 53.6% at maximum reasoning effort. An agentic setup with dynamic visual manipulation narrows but does not close the gap, the researchers say.

Research Foundation Models Computer Vision

Gatewai Launches Framefields Beta for Native WebGPU Video Rendering in Node.js

Oct 06, 2026

GitHub

Gatewai launches the beta of Framefields, an Apache-2.0 Node.js package that renders code-first video directly via WebGPU, Dawn, Metal or Vulkan instead of headless Chromium, while offering on-device ONNX vision tools for segmentation, pose tracking and person mattes.

Image & Video Coding & Developer Tools Computer Vision Open Source

AMD Agrees to Buy AI Lab World Labs for $8.2 Billion, Bringing Fei-Fei Li On as Chief Scientist

Sep 29, 2026

Advanced Micro Devices, Inc.

AMD agrees to acquire spatial-intelligence startup World Labs for about $8.2 billion in stock, with co-founder Fei-Fei Li set to become executive vice president and chief scientist reporting to CEO Lisa Su after the deal closes by the end of 2026.

Business Computer Vision Robotics

Meta Launches SAM 3.1 API for Zero-Shot Object Detection, Segmentation and Video Tracking

Sep 21, 2026

Segment Anything Model (SAM) 3.1 | Meta | Meta

Meta launches the SAM 3.1 API, letting developers use text prompts to detect, segment and track objects across video while preserving identity, with no model hosting or fine-tuning required and pricing starting at $2.50 per 1,000 images.

Computer Vision Coding & Developer Tools

Alibaba’s Damo Academy Open-Sources AI Model That Detects Nearly 150 Abdominal Conditions in CT Scans

Sep 21, 2026

South China Morning Post

Alibaba’s Damo Academy open-sources Damo Radar, an AI model that analyzes contrast-enhanced CT scans across 18 abdominal organs to detect 146 findings—including cancers—with a reported average AUC of 0.913 in nearly 40,000 real-world examinations.

Healthcare Open Source Computer Vision

Qwen-Drive-1.0 Launches as a Unified AI Model Combining 3D Perception and Motion Planning for Autonomous Driving

Sep 08, 2026

GitHub

Qwen-Drive-1.0 launches as a powerful unified AI model combining 3D perception, visual question answering, and motion planning for autonomous driving, outperforming competitors on major benchmarks and now freely available under an open-source license.

Autonomous Vehicles Foundation Models Open Source Computer Vision