aiqbench takeAI Products

Black Forest Labs' FLUX 3 Action introduces a significant efficiency breakthrough in robot control by jointly predicting future video frames and actions within a single 7B parameter model. By leveraging extensive pretraining on multimodal data, it outperforms leading open-weight policies like NVIDIA's Cosmos 3 Nano on the RoboLab-120 benchmark while reducing computational overhead through architectural distillation. This advancement demonstrates that high-fidelity world modeling can be decoupled from massive compute requirements, offering a viable path toward scalable, deployable robotic agents.

Source coveringMarkTechPost

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120

MarkTechPostSeptember 25, 20264 min read

Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3 Action. It is a 7B open-weights World Action Model (WAM) for robot control. The model reads camera frames, robot state and a text instruction. It then predicts future video frames and the next chunk of actions together. On the RoboLab-120 […] The post Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120 appeared first on MarkTechPost.

Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3 Action. It is a 7B open-weights World Action Model (WAM) for robot control. The model reads camera frames, robot state and a text instruction. It then predicts future video frames and the next chunk of actions together. On the RoboLab-120 leaderboard, it ranks first at 42.92% task success. Is it deployable? Yes, with conditions. The DROID policy needs about 32 GB of GPU memory in…

Excerpt shown under the publisher's RSS terms · 80 words · full text and figures are on the publisher's site

Read at MarkTechPost ↗Ask about this article