arXiv AI August 18, 2026 By Yufei Guo, Yinan Wu, Haoran Duan, Guiguang Ding, Jungong Han

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

arXiv:2608. 15285v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temporally static updates throughout a control rollout, overlooking the phase-dependent nature of continuous-action manipulation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 2

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

arXiv:2605. 13548v3 Announce Type: replace-cross Abstract: Existing robotic foundation models, while powerful, are predicated on an implicit assumption of temporal homogeneity: treating all actions as equally informative during optimization.

By Daojie Peng, Fulong Ma, Jiahang Cao, Qiang Zhang, Xupeng Xie, Jian Guo, Ping Luo, Andrew F. Luo, Boyu Zhou, Jun Ma

robotics multimodal benchmarks

arXiv AI

Jul 31

DLAM: Distributional Latent Actions with Temporal Constraints

arXiv:2607. 27138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change.

By Zuojin Tang, Feifan Luo, Haoyun Liu, Botai Yuan, Dekang Qi, Ronghan Chen, Yandan Yang, Tong Lin, Xinyuan Chang, Mu Xu, Bin Liu, De Ma, Zhiheng Ma

robotics multimodal

arXiv AI

Jul 29

InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation

arXiv:2606. 12109v2 Announce Type: replace-cross Abstract: Pre-trained Vision-Language-Action (VLA) models provide useful semantic and spatial priors, yet their parallel-gripper action interfaces do not specify how those priors should be realized by a dexterous hand.

By Chuanke Pang, Junyi Huang, Zhijun Zhao, Yaobing Wang, Kun Xu, Xilun Ding

diffusion robotics multimodal

arXiv AI

Jun 29

S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

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

robotics multimodal benchmarks

arXiv AI

Jul 22

AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models

arXiv:2604. 17787v2 Announce Type: replace-cross Abstract: Precision-critical manipulation requires both global trajectory organization and local execution correction, yet most vision-language-action (VLA) policies generate actions within a single unified space.

By Tingzheng Jia, Kan Guo, Lanping Qian, Yongli Hu, Daxin Tian, Guixian Qu, Chunmian Lin, Baocai Yin, Jiapu Wang

diffusion robotics multimodal

arXiv Machine Learning

Jul 14

On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation

arXiv:2607. 10172v1 Announce Type: cross Abstract: Deploying billion-parameter Vision-Language-Action (VLA) models on industrial hardware requires fine-tuning to bridge the embodiment gap.

By Finn Ferchau, Daniel Pommer, Cristian Axenie

robotics fine-tuning multimodal

Related stories

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

DLAM: Distributional Latent Actions with Temporal Constraints

InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation

S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models

On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation