AnyviewMeter is a geometry‑conditioned adaptation framework that fine‑tunes pretrained robotic reward models to account for camera viewpoint and occlusion. It uses low‑rank fine‑tuning, token‑aligned Plücker rays, and synchronous block attention to fuse synchronized multi‑view observations. Experiments on PickCube and simulated manipulation tasks show significant reductions in mean absolute error and improved temporal ordering compared to single‑view or RGB‑only fine‑tuning.
By Yuang Tu, Runjia Tan, Yujie Yan, Jinghan Hu, Chen Lv
arXiv:2510. 01711v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs).
By Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin
RawVLA introduces a streaming neural image signal processor that adaptively renders RAW observations for vision‑language‑action (VLA) policies, focusing on imaging factors that influence embodied behavior. The authors systematically analyze how five ISP dimensions—gain, sensor noise, chromatic response, tonal response, and bit depth—affect action prediction and manipulation success, showing that RAW‑to‑RGB processing significantly shapes outcomes. They also present RawVLA‑Bench, a RAW‑domain manipulation benchmark that evaluates image processing as an explicit variable across clean and adverse conditions, demonstrating that RawVLA maintains performance under standard settings while markedly improving robustness under degraded imaging.
By Shuhong Liu, Heng Zhou, Lingfeng Qian, Yuhao Fang, Xianbao Hou, Qianyu Zhou, Lin Gu, Wei Sui, Jianfei Yang, Ziteng Cui
arXiv:2607. 20785v1 Announce Type: cross Abstract: Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently.
By Arjun Majumdar, Avinash Sooriyarachchi, Benjamin Tibi, Chris Bamford, Elliot Chane-Sane, Guillaume Lample, Khyathi Raghavi Chandu, Ludovic Ho Fuh, Mathieu Poiree, Olivier Duchenne, Rosalie Millner, Srijan Mishra, Theo Cachet, Thomas Chabal
The paper investigates how Vision‑Language‑Action (VLA) models can generalise across different driving environments and camera setups. It introduces a multi‑dataset training strategy and an auxiliary objective called BEV‑Forcing, which injects bird‑eye‑view spatial information into the VLA backbone to improve both in‑distribution and out‑of‑distribution performance on a limited number of camera rigs. The authors observe that while BEV‑Forcing helps when training data is scarce, its advantage diminishes as the number of training embodiments grows, suggesting that scaling diversity may reduce the impact of such auxiliary tasks.
By Caio Azevedo, Stefano Sabatini, Sascha Hornauer, Fabien Moutarde
arXiv:2606. 27872v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, but their performance degrades significantly in long-horizon tasks due to cumulative error propagation.
By Zhipeng Xie, Zongyi Han, Xiangyi Wei, Shiliang Sun, Yang Li, Jing Zhao
arXiv:2609.13235v1 Announce Type: cross
Abstract: Networked manipulation endpoints couple perception to actuation across compute- and bandwidth-limited links, yet commonly exchange dense geometric st...
By Md Selim Sarowar, Sungho Kim
arXiv:2610.03710v1 Announce Type: cross
Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. E...
By Kush Hari, Justin Kerr, Nidhya Shivakumar, Samarth Mahapatra, Carmelo Sferrazza, Jiahui Lei, Jitendra Malik, C. Karen Liu, Ken Goldberg, Angjoo Kanazawa
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
arXiv:2606. 12105v1 Announce Type: cross Abstract: Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate.
By Pankhuri Vanjani, Zhuoyue Li, Jakub Suliga, Moritz Reuss, Gianluca Geraci, Xinkai Jiang, Rudolf Lioutikov
arXiv:2601.17885v2 Announce Type: replace-cross
Abstract: Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Exis...
By Qingyu Fan, Zhaoxiang Li, Jinrui Hu, Yi Lu, Wang Chen, Qiu Shen, Xiao-xiao Long, Yinghao Cai, Tao Lu, Shuo Wang, Xun Cao
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.