AI Image Generators
AI image generators create pictures from a text prompt: Midjourney, Stable Diffusion, FLUX, DALL-E and Nano Banana turn a description into an illustration, photo or artwork in seconds. The quality now rivals professional design work, while courts sort out copyright. Here is all our coverage of image generation: model releases, comparisons, pricing and legal battles.
HiSTEVE 1.0 Plays Minecraft With a Mouse and Keyboard: 85.0% on MineStudio Bench
VLA agent HiSTEVE 1.0 completes long Minecraft tasks with no API and no hidden game state: 85.0% on MineStudio Bench, 37.4% on OpenHA, and an iron pickaxe from…
Survey by Shengqiong Wu and Hao Fei: 600+ Papers on Video Models as World Models
A team including Shuicheng Yan, Ming-Hsuan Yang and Philip Torr unifies video understanding and generation in one framework and reviews more than 600 papers across…
LeWorldModel Tested for Action Sensitivity: Axes Diverge by 36–42°
Preprint authors compared how LeWorldModel and the simulator respond to small action changes. The principal sensitivity axes diverge by 36° in Reacher and 42° in…
LEGO-SCD learns to detect changes in 3D scenes at 17.2 FPS without manual labeling
Six Teams from UCSB, Stanford and J.P. Morgan Release an Agent Memory Benchmark
Dream Labs, from the NVIDIA DreamZero team, raises $90M and opens an API for robots
HyperDrone Renders Millions of Frames per Second and Outpaces Rivals by 20x
RoboJudge-9B Judges Robot Videos More Accurately Than Gemini: 0.719 Correlation With Humans
CUHK researchers built an 800-video annotated benchmark and trained a 9B judge for robot videos: 0.719 correlation with humans, 0.089 higher than Gemini-3.7-Flash.
Black Forest Labs: A 70-Person Team Takes On Silicon Valley's Giants
Black Forest Labs, known for its image generation success, is widening its scope. Its next target is bringing AI into the physical world and robotics.
OpenVLHarness Gives Multimodal Models Memory and Tools: +9.7–12.6 Points
Stateful Harness Lifts World Model Accuracy on Hidden State from 32% to 92%
Halcyon beats LlamaGen and JiT-T2I with 18–275x less pretraining compute
ActionRoPE Turns Player Actions into Coordinates and Cuts Scene Drift by 66%
Stanford Online Posts Lecture 12 of AA274A: Classical Computer Vision for Robots
Marco Pavone's lecture from the 2019 Principles of Robotic Autonomy course covers information extraction and classic visual recognition. The textbook is open, and…
Why Multimodal Models Can't See Web Interfaces
Multimodal models struggle with interfaces: code hides reality, and screenshots require analyzing millions of pixels. What's needed is a built-in module for…