Tag
Starting from a single scouting photo, the team compared several directions—including a portal concept where crumbling bricks reveal another world—before settling on a final design.
Ten days after teaming up with France's Mistral, Saudi Arabia's state AI company has now built on a Chinese open model
Across 7.1 million verification images, a training-free discriminator matched or beat existing detectors
Fei-Fei Li's World Labs has rolled generation, reconstruction, and robot simulation into a single model called Atlas
Nick Tasker's 30-second ad "Let's Give Chicken a Break" went from a single base image straight through to final grading
Alibaba's specialized retraining for coding and collaboration reclaims the top spot on WorkArena, though terminal coding still lags
vLLM-Omni and FastVideo's FastH3 have pushed generation time below the video's own runtime
Google has added a new processing mode to Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite that lets the model pick out only the parts of a video it actually needs.
The company introduced an "interface world model" that generates interfaces frame by frame in real time, with no code involved
In an interview video released by Google DeepMind, the robot Apollo said tying a trash bag was harder than balancing during sports
From ninja action to a beverage ad to a yakuza-style cinematic, Higgsfield shows how to turn Blender 3D blocking into Seedance 2.5 video.
The 125B MoE model runs on RAM alone with no GPU required, and it beat Claude Opus 4.6 Max across several benchmarks
