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.
Google DeepMind and Biohub Explain Why AlphaFold Didn't Close the Protein Folding Problem
Pushmeet Kohli of DeepMind and Sal Candido of Biohub break down what AlphaFold left unsolved after the Nobel Prize and 200+ million predicted structures.
CISPA Researcher Tests Whether AI Image Watermarks Survive Training of New Models
Michel Meintz of CISPA's SprintML Lab studied whether watermarks on AI images persist after a new generative model is trained on them. The answer depends on the…
Three Major Publishers Quietly Roll Out LLMs, and Staff Are Angry
Employees at three major publishers told WIRED that AI already writes marketing copy, makes cover art and answers email, while senior managers lean on junior staff.
Google Launches The Talking Museum: 3D Artifacts You Can Question with Gemini
Aether AI shows a manipulator with a causal core in a seven-minute video full of interference
MWS AI Tests Multimodal Models on Detecting Forged Documents
8B RL-Trained Agent Teaches a Video Model to Look Up Data and Compute Physics
Doubao adds an infinite canvas for creative work and a 2.1 Lite model
ByteDance's Doubao work mode gets a Canvas feature for complex creative tasks and a lightweight Doubao 2.1 Lite model. Everything sits on one infinite page.
Video Generation With an Expression Gallery Beats Baseline Models on Identity Similarity
A single portrait is not enough for a model to preserve identity in video. A reference set with varied expressions raises face similarity in every mode, most of all…
PCAsplat Cleans Up Gaussian Splat "Floaters" With Local PCA on Three Benchmarks
Researchers Extend DINOv2's CLS Token with Regions of Interest for Image Retrieval
Omni-Diffusion-Distill speeds up multimodal dLLMs by up to 21x: 8 steps instead of 128
Fluid-Gen-Zero hands water physics to a simulator and cuts fluid flow error by 84%
SPLIT-RL Teaches VLMs to See and Reason Separately: +1.4–6.1 pp Over GRPO
SPLIT-RL, a new post-training scheme, splits vision-language model training into perception and reasoning phases and beats GRPO by 1.4–6.1 points on Qwen3-VL and…
Flow matching: velocity scaling cuts FID from 28.0 to 12.2 on ImageNet-256
An arXiv paper attributes the velocity-scaling effect in flow matching to a population time lag, not to underestimated velocity. FID on ImageNet-256 fell from 28.0…