world models

Google's updated Genie 4 points to new uses for world models in robotics and AI testing, according to AI Business. The outlet says enterprises must weigh that potential against accuracy gaps.

Tencent Hunyuan posted the Hy-Nomas technical report to arXiv on October 27 and released Hy-Nomas-Bench, a 280-case benchmark for interactive video world models. Hy-Nomas is an 8B diffusion world model, released with code and weights on October 21 under Apache 2.0.

Kyutai released CADRE, a family of 7 open causal diffusion video autoencoders built for interactive world models. World models built on CADRE run at 20 fps on 1 H100 and react in under 230 ms, according to MarkTechPost's report.

NVIDIA has expanded the Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints. The company says Cosmos ranks in the top five on six different open model leaderboards.

Google DeepMind says Gemini 4 Argon scores 87% on the Embodied Reasoning (ERQA) benchmark using pure reasoning, ahead of every other frontier model. A new robotics post demonstrates robot control, Real2Sim reconstruction, physical understanding, and self-improvement workflows. Pricing, context window, and availability were not disclosed.

Reka AI has released a research preview of Rho-1, a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions in a single network. Reka says it uses no tool calls or external models. Context window, pricing, and benchmark scores have not been disclosed.

Black Forest Labs has released FLUX 3 Action, an open-weight robotics model built on its FLUX 3 multimodal foundation. The 7-billion-parameter model reads multi-camera video feeds and predicts what a robot should do next, claiming a record success rate on the RoboLab-120 leaderboard while running nearly 4x faster than the previous best open model.

Runway has shared research into generating video frame by frame in real time, letting users steer output as it streams rather than waiting for a finished clip. The approach builds on GWM-1, Runway's General World Model introduced in December 2025, and no availability timeline has been announced.

World Labs, co-founded by Fei-Fei Li, has released Atlas, an omni-model that generates camera-controlled video, reconstructs 3D scenes from as few as two images, and simulates environments for robot training. The company claims Atlas outperforms specialized 3D and video models on internal benchmarks, though it is currently limited to an early-access program.

Black Forest Labs has released Flux 3, a multimodal foundation model trained jointly on images, video, and audio that generates videos up to 20 seconds long with synchronized native audio. The company also introduced Flux-mimic, a robotics action model already being tested at Audi.

Yann LeCun, former Meta chief AI scientist and founder of AMI Labs, called Elon Musk's xAI a "failure" that won't be able to compete with OpenAI and Anthropic. LeCun warned that AI labs are at risk of a "big bubble explosion" because current pricing doesn't cover operational costs, with services funded primarily by investors.