VersaCamVLA introduces a camera‑configurable framework that separates camera‑set representation from action learning in Vision‑Language‑Action models. It learns a unified scene‑token interface that maps any number of posed RGB views into fixed‑size latent tokens using multi‑signal target‑view prediction and Wrist‑Augmented Pose Sampling. At deployment, a lightweight spatial encoder injects these tokens into a pretrained VLA, enabling robust manipulation without explicit 3D sensing or novel‑view rendering, and consistently outperforms prior methods across varying camera counts and unseen poses.
By Boyao Han, Chen Shi, Jingjing Qian, ZhuoTan Tian, Li Jiang
arXiv:2609.23565v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot contr...
By Yuxuan Jiang, Jiaying Huang, Ge Wang, Shenhao Yan, Jiahao Yang, Chengsi Yao, Qi Liu, Qing Zhao, Shuguang Cui, Yiming Zhao, Yatong Han, Zhen Li
arXiv:2607. 05396v1 Announce Type: cross Abstract: Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios.
By Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Shijian Lu, Gongjie Zhang, Ran Xu
arXiv:2606. 20118v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution.
By Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon, Minha Lee, Jinwoo Shin
Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing view-robust Vision-Language-Action (VLA) policies tolerate such camera variations only when the camera extrinsics are explicitly provided, making them fragile and hard to use especially when view robustness is critical.
InfiNoVA is a data‑augmentation framework that transforms synchronized multi‑camera demonstrations into a dense, geometrically consistent set of training views by reconstructing each manipulation trajectory as a time‑varying 3D Gaussian. The method renders novel observations from sampled camera poses while preserving the original state‑action pairs, improving frame‑level fidelity and temporal consistency compared to generative synthesis. Across four real‑world manipulation tasks, policies trained with InfiNoVA achieve 5.4× higher average success under unseen randomized viewpoints than VISTA‑based augmentation and 1.7× higher success than training on all five physical camera views.
By Sai Puneeth Reddy Gottam, Elmar Rueckert, Vedant Dave
Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions.
arXiv:2606. 04708v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging.
By Siyuan Yang, Linzheng Guo, Ouyang Lu, Zhaxizhuoma, Daoran Zhang, Xinmiao Wang, Ting Xiao, Fangzheng Yan, Zhijun Chen, Yan Ding, Chao Yu, Chenjia Bai, Xuelong Li
GS‑VLA introduces a lightweight, plug‑and‑play framework that uses a 4 M‑parameter 3D‑Gaussian canonicalizer to adapt frozen Vision‑Language‑Action (VLA) policies to viewpoint shifts without retraining the policy. By treating viewpoint changes as a localized novel‑view synthesis problem under a locality assumption, the method normalizes observations through a scene‑ and policy‑independent disocclusion task. Experiments on the LIBERO benchmark demonstrate that GS‑VLA recovers a large portion of performance lost due to camera displacement, improving results across different policy architectures, unseen task suites, and perturbation scales.
whyItMatters":"The approach offers a computationally efficient alternative to costly fine‑tuning or generative augmentation, enabling robust VLA deployment in real‑world settings where camera configurations may vary."
By Yechan Park, HyunJin Kim
The paper introduces Self‑Adaptive VLA, a post‑training method that lets Vision‑Language‑Action policies self‑adapt to deployment‑time hardware shifts by using rollouts as context. It creates shift‑conditioned expert demonstrations, compresses visual, proprioceptive, and action data into a latent context token, and modulates the policy via adaptive layer normalization. Experiments on four precision‑critical manipulation tasks show the method recovers over 80 % of the base policy’s performance under actuation bias and encoder offsets, and improves robustness on new workstations.
By Hongxin Zhang, Chunru Lin, Tsun-Hsuan Wang, Zhenjia Xu, Chuang Gan
arXiv:2609.38443v1 Announce Type: cross
Abstract: We introduce BIND, a new action representation for visuomotor robot policies that binds 3D robot actions to their corresponding 2D image features, yi...
By Cameron Smith, Arsh Tangri, Vitor Guizilini, Yue Wang, Zubair Irshad, Sergey Zakharov
arXiv:2607. 11498v1 Announce Type: cross Abstract: Vision-language-action (VLA) models predict robot actions from visual observations and language instructions.
By Byungkun Lee, Dongyoon Hwang, Dongjin Kim, Hojoon Lee, Minho Park, Jaegul Choo