FLUX 3 Action
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 2
- Runway open-sources the Praxis-1 robot world-action model
Runway released Praxis-1’s model weights and source code under the Apache 2.0 license, allowing commercial use and local fine-tuning. The 27-billion-parameter MoE diffusion Transformer jointly predicts video and robot actions from camera images, text instructions, and position data, but the base model still requires additional robot-specific training. Runway reported a 46.2% success rate on RoboLab-120, ranking first in the World Action Model category but fifth overall, with the results not independently verified.
The Decoder · 🔥 0 - Stanford's Fei-Fei Li team open-sources OpenWAM world-action model framework
A Stanford team including Fei-Fei Li, Jiajun Wu and Ehsan Adeli published OpenWAM, an open framework for composable world-action models that aims to disentangle the many ways video prediction and action generation can be coupled in this emerging class of robot policies. OpenWAM starts from Alibaba's open Wan2.2-5B video model, continues pretraining on roughly 3.34 million robot-and-human interaction videos (nominally about 14,600 hours) for 14 days on 32 B200 GPUs, then joins a 5B video expert with a 2B action expert via a shared Mixture-of-Transformers architecture with four configurable interaction orders (VTA, ATV, Joint, Decoupled). The authors report 98.6% average success for VTA across the four LIBERO subsets and 92.1% / 91.9% average success for VTA and Joint on three real dual-arm Franka FR3 tasks, plus a LIBERO-Long-CF counterfactual dataset; training, evaluation and composition code and pretrained video weights are open-sourced.
36氪 人工智能 · 🔥 0
Experience and discussion from the community
Share my FLUX 3 Action experienceAsk about FLUX 3 Action
Nobody has shared their experience with FLUX 3 Action yet.