AI News Zhipu AI Releases ‘Glyph’: An AI Framework for Scaling the Context Length through Visual-Text Compression Oct 30, 20254 min read
AI News Salesforce AI Research Introduces WALT (Web Agents that Learn Tools): Enabling LLM agents to Automatically Discover Reusable Tools from Any Website Oct 25, 20254 min read
AI News NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI Oct 10, 20255 min read
AI News Meta AI Researchers Release MapAnything: An End-to-End Transformer Architecture that Directly Regresses Factored, Metric 3D Scene Geometry Oct 5, 20254 min read
AI News IBM AI Releases Granite-Docling-258M: An Open-Source, Enterprise-Ready Document AI Model Sep 30, 20253 min read
AI News How to Master Advanced TorchVision v2 Transforms, MixUp, CutMix, and Modern CNN Training for State-of-the-Art Computer Vision? Sep 25, 20257 min read
AI News What are Optical Character Recognition (OCR) Models? Top Open-Source OCR Models Sep 15, 20252 min read
AI News Apple Released FastVLM: A Novel Hybrid Vision Encoder which is 85x Faster and 3.4x Smaller than Comparable Sized Vision Language Models (VLMs) Sep 10, 20253 min read
AI News AI and the Brain: How DINOv3 Models Reveal Insights into Human Visual Processing Sep 5, 20254 min read
AI News VLM2Vec-V2: A Unified Computer Vision Framework for Multimodal Embedding Learning Across Images, Videos, and Visual Documents Aug 31, 20253 min read
AI News Meta CLIP 2: The First Contrastive Language-Image Pre-training (CLIP) Trained with Worldwide Image-Text Pairs from Scratch Aug 26, 20253 min read
AI News Qwen Team Introduces Qwen-Image-Edit: The Image Editing Version of Qwen-Image with Advanced Capabilities for Semantic and Appearance Editing Aug 21, 20254 min read
