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.
Moonshot Releases WorldVQA: 3500 Questions About the World That Trip Up Models
The Kimi team published WorldVQA, a benchmark of 3500 image-question pairs. On rare objects, top multimodal models often fall short of 50% accuracy.
Kimi releases PerceptionBench: none of 16 MLLMs reaches 60%
Moonshot released a 3000-question benchmark where the answer is visible to the eye. None of 16 top multimodal models scored 60%, and hallucinations are the weakest…
LabBuilder Turns an Experiment Description into a Safe 3D Lab
A team at ICML 2026 introduced LabBuilder, a system that builds a safety-aware 3D lab layout from the text of an experiment protocol. The authors name three gaps in…
MTEdit: 500 thousand editing trajectories teach models not to lose quality over 8 steps
Xiaomi-Lens-0, a 4B model, beats Qwen3.5 by 5.6 points on RefCOCO
MARS Transfers Text-Based Refusal to Video and Images Without Data: A Test on 5 MLLMs
MambaAct speeds up π0.5 robots: action expert 10x smaller, latency down 64.8%
Tadpole Proposes a Foundation Model for Physics: From Prediction to Understanding
Tadpole brings foundation-model logic to science: one model instead of separate networks for weather, airflow, material deformation and electromagnetism.
Artificial Analysis Launches AA-Robotics, Tests GPT, Claude and Gemini as a Robot's Brain
On October 14, Artificial Analysis released AA-Robotics, its first robotics benchmark. General-purpose LLMs now sit an exam once seen as the territory of…
Apple's LensVLM compresses long agent context into images and teaches the model to "zoom"
AA-Robotics v0.1: GPT-6 Astra controls a robot arm and scores 69 out of 100
BlenderWorld: GPT-6-Astra Beats Opus-5 in 3D Benchmark with a Score of 79.9
Modal raises $750M at $15.75B valuation and reaches $1B run rate
KANLab: A TensorFlow Playground Fork That Shows KAN Training in the Browser
Lukas Niehaus and colleagues released KANLab: a small Kolmogorov–Arnold network trains in the browser, and every B-spline curve can be viewed and edited by hand.
Isomorphic Labs Uses Gemini 4 Argon to Parse 500-Page Patents in a Day Instead of a Month
Isomorphic Labs researchers apply the multimodal Gemini 4 Argon to chemical patents: a structured report takes one day instead of a month of manual reading.