arXiv:2607. 27933v2 Announce Type: replace Abstract: Flow matching (FM) has become a popular action head paradigm for modern embodied models.
By Ziyang Rao, Yiren Zhao, Weiyu Guo, Ben Fei, Yandong Guo, Hui Xiong
arXiv:2607. 27933v3 Announce Type: replace Abstract: Flow matching (FM) has become a popular action head paradigm for modern embodied models.
By Ziyang Rao, Yiren Zhao, Weiyu Guo, Ben Fei, Yandong Guo, Hui Xiong
arXiv:2606. 18043v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets.
By Ralf R\"omer, Maximilian Seeliger, Saida Liu, Ben Sturgis, Marco Bagatella, Daniel Marta, Andreas Krause, Angela P. Schoellig
Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets. Despite their strong empirical performance in robotic manipulation, VLAs lack mechanisms to quantify confidence in their predictions and to detect when their actions may be unreliable.
GeoAAC introduces a geometry-based adaptive action chunking technique for Vision‑Language‑Action policies, dynamically adjusting the action horizon based on the reliability of current action predictions. By leveraging the geometric variation in Flow Matching denoising trajectories, GeoAAC constructs a horizon‑wise geometric profile that determines the action horizon during a single generation without extra training. Experiments on LIBERO, LIBERO‑Pro, RoboCasa365, and real‑world manipulation tasks demonstrate consistent gains over fixed‑horizon baselines, achieving up to 8.7 percentage points improvement in simulation and raising real‑world success rates from 53.3% to 74.4%.
By Xin Chen, Sen Chen, Yujuan Ding, Jian Liu, Guoqing Wang, Wei Ye, Heng Tao Shen, Yi Bin
arXiv:2605. 00941v4 Announce Type: replace Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem.
By Jiarui Xing, Song Wang, Jian Wang