AI News Microsoft Research’s World-R1 Uses Flow-GRPO and 3D-Aware Rewards to Inject Geometric Consistency Into Wan 2.1 Without Architectural Changes May 17, 20265 min read
AI News Salesforce AI Introduces FOFPred: A Language-Driven Future Optical Flow Prediction Framework that Enables Improved Robot Control and Video Generation Jan 23, 20266 min read
AI News Black Forest Labs Releases FLUX.2 [klein]: Compact Flow Models for Interactive Visual Intelligence Jan 18, 20264 min read
AI News Thinking Machines Lab Makes Tinker Generally Available: Adds Kimi K2 Thinking And Qwen3-VL Vision Input Dec 19, 20255 min read
AI News Zhipu AI Releases GLM-4.6V: A 128K Context Vision Language Model with Native Tool Calling Dec 9, 20255 min read
AI News Google AI Introduces VISTA: A Test Time Self Improving Agent for Text to Video Generation Dec 4, 20255 min read
AI News Black Forest Labs Releases FLUX.2: A 32B Flow Matching Transformer for Production Image Pipelines Nov 29, 20253 min read
AI News Meta AI Releases Segment Anything Model 3 (SAM 3) for Promptable Concept Segmentation in Images and Videos Nov 24, 20255 min read
AI News A Coding Guide to Implement Advanced Hyperparameter Optimization with Optuna using Pruning Multi-Objective Search, Early Stopping, and Deep Visual Analysis Nov 19, 20256 min read
AI News Baidu Releases ERNIE-4.5-VL-28B-A3B-Thinking: An Open-Source and Compact Multimodal Reasoning Model Under the ERNIE-4.5 Family Nov 14, 20254 min read
AI News Why Spatial Supersensing is Emerging as the Core Capability for Multimodal AI Systems? Nov 9, 20256 min read
AI News UltraCUA: A Foundation Computer-Use Agents Model that Bridges the Gap between General-Purpose GUI Agents and Specialized API-based Agents Nov 4, 20254 min read
