English(EN)NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields
新的VLA模型增强机器人推理、安全性和效率 · 跟踪10个来源
作者PulseAugur 编辑部·[31 个来源]·
研究人员正在为机器人技术开发先进的视觉-语言-动作（VLA）模型，重点是提高推理、安全性和效率。TOAST和TRUST等新方法旨在通过引入随机性和监控推理过程来增强策略学习和运行时安全性。其他进展包括用于城市导航的专用模型（UrbanVLA）、可泛化的奖励生成（Large Reward Models）以及节能的脉冲驱动架构。此外，还在努力改进VLA系统中的多智能体协调和长时任务规划。
AI
arXiv:2610.00601v1 Announce Type: cross Abstract: Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for runtime safety through reasoning monitoring and correction. In this work, we de…
arXiv:2603.16065v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown strong potential for improving robotic manipulation policies, yet its practical use remains bottlenecked by the difficulty of specifying reward functions that are both semantically mea…
arXiv:2510.23576v2 Announce Type: replace-cross Abstract: Urban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following long-horizon route instructions. This task is particularly challenging due to the …
arXiv:2610.00899v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with standard next-token objectives. FAST has substantially improved this representation…
arXiv:2609.39514v1 Announce Type: new Abstract: Vision-language-action (VLA) models bridge multimodal understanding and robotic control, advancing the dominant paradigm for embodied intelligence. However, most existing models rely on large Transformers, whose latency and energy c…
arXiv cs.AI
TIER_1English(EN)·Ruixiao Xu, Wong Lik Hang Kenny, Zhiqian Liu, Jianing Guo, Hanxiao Li, Kejian Shi, Shuning Zhang, Pu Feng, Yongjia Ma, Yuqing Ma, Kai Chen, Qi Dou, Yaodong Yang, Xianglong Liu, Simin Li·
arXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on large-scale single-agent data and therefore lack the fine-gra…
arXiv cs.AI
TIER_1English(EN)·Shizhe Chen, Ricardo Garcia, Paul Pacaud, Cordelia Schmid·
arXiv:2506.11261v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have shown promising progress in robotic manipulation. However, directly mapping visual observations and language instructions to low-level actions often results in limited interpretabil…
arXiv cs.AI
TIER_1English(EN)·Tuan Duong Trinh, Basim Azam, Mohammed Ishaq Ansari, Mohammed Yaqoob Ansari, Naveed Akhtar·
arXiv:2603.12717v2 Announce Type: replace-cross Abstract: Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are designed to reason in text before acting, generating a reasoning chain and decoding…
arXiv cs.CL
TIER_1English(EN)·Haotian Deng, Wenbin Xing, Gang Xu, Tao He, Jinkai Zheng, Chun Li, Zheng Zhu, Ming Li·
arXiv:2609.37837v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses. Existing safety methods often require large preference dat…
arXiv cs.LG
TIER_1English(EN)·Ziyi Yin, Sangmin Woo, Kang Zhou, Sungyeon Kim, Aosong Feng, Haibo Ding, Jun Huan·
arXiv:2609.36352v1 Announce Type: cross Abstract: Vision-language-action (VLA) models perform well on shorter-horizon manipulation tasks but still struggle with long-horizon tasks that require multiple dependent manipulations from a single command. Online reinforcement learning (…
arXiv cs.LG
TIER_1English(EN)·Junghyun Kim, Ngseo Kim, ChungWoo Lee, Seoyeon Lee, Woo-Jeong Baek, Adam Zhou, Chip Huyen, Jun-Ki Lee, Gi-Cheon Kang, Byoung-Tak Zhang·
arXiv:2609.37165v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models remain brittle under visual distribution shifts, often relying on spurious correlations tied to domain-specific factors rather than task-relevant structure. We propose Domain-Invariant Latent Lo…
arXiv cs.LG
TIER_1English(EN)·Shengchao Hu, Peng Wang, Qiyang Zhou, Guodong Zheng, Yuqi Huang, Li Shen, Ya Zhang, Dacheng Tao·
arXiv:2609.35965v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) has largely focused on a single agent following a single instruction, yet many real-world applications require teams of robots to tackle tasks beyond the capabilities of any individual agent. W…
arXiv:2609.30996v1 Announce Type: cross Abstract: The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on semantic information through the internal representations of large language models (LLMs). A growing body of work has begun ext…
arXiv:2606.21372v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models rely on discrete action tokenizers to bridge continuous robot control and autoregressive sequence modeling, yet existing tokenizers often trade off between compression, latency, and down…
We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on large-scale single-agent data and therefore lack the fine-grained coordination skills required for inter-robot …
Vision-language-action (VLA) models perform well on shorter-horizon manipulation tasks but still struggle with long-horizon tasks that require multiple dependent manipulations from a single command. Online reinforcement learning (RL) can improve these policies through environment…
Vision-language-action (VLA) models have achieved strong performance in language-conditioned manipulation, yet success under nominal evaluation does not necessarily translate into robust closed-loop behavior when executed actions are transiently corrupted. We introduce DS-VLA, a …
arXiv:2610.01180v1 Announce Type: new Abstract: Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently struggle to understand negation and produce incorrect answers when questions involve…
arXiv cs.CV
TIER_1English(EN)·Yijie Zhu, Rui Shao, Jie He, Wei Li, Bo Zhao, Yelin Wang, Xiaochen Yuan, Tao Tan, Miao Zhang, Xiaojiang Peng, Zitong Yu·
arXiv:2610.01741v1 Announce Type: new Abstract: Predictive Vision-Language-Action (VLA) models aim to improve robotic manipulation via future observation or world dynamics forecasting. However, existing approaches often fail to realize this potential and underperform direct actio…
arXiv cs.CV
TIER_1English(EN)·Shota Kobayashi, Koki Seno, Daichi Yashima, Komei Sugiura·
arXiv:2610.00981v1 Announce Type: cross Abstract: We focus on language-conditioned flow-based manipulation, where robot flows (robot velocity fields) serve as embodiment-agnostic, motion-centric representations for leveraging data collected from multiple robot platforms. This tas…
arXiv cs.CV
TIER_1English(EN)·Hongyi Cai, Yi Herng Ong, Tingshiuan C. Wu, Chiew Hui Lim, Hanxia Li, Kehong Guo, Sze Yuan Cheong·
arXiv:2609.32193v2 Announce Type: replace Abstract: Vision Language Action (VLA) models condition actions directly on current visual and language context, without an explicit account of how the scene evolves under candidate actions. World Action Models (WAM) attempt to address th…
arXiv:2601.22153v2 Announce Type: replace-cross Abstract: Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models. Although recent VLAs generalize well in static manipulation, dynamic scenes introduce a latency-induced perception-execution m…
arXiv:2609.39794v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, yet adapting them to new tasks and domains remains inefficient: existing methods often rely on parameter tuning, incurring subst…
arXiv cs.CV
TIER_1English(EN)·Kai Yan, Xiangyu Chen, Yulong Cao, Alex Naumann, Peter Karkus, Yan Wang, Jef Packer, Alex Schwing, Yuxiong Wang, Boris Ivanovic, Wenjie Luo, Marco Pavone·
arXiv:2609.38641v1 Announce Type: new Abstract: Vision-Language-Action (VLA) foundation models have recently emerged as one of the prevailing solutions for autonomous driving, as they can utilize knowledge acquired during vision-language pretraining for accurate and interpretable…
arXiv cs.CV
TIER_1English(EN)·Jingqiu Wang, Yan Wang·
arXiv:2609.39324v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently incorporated world models to provide richer dynamic supervision beyond sparse action labels. However, explicitly predicting future images or videos may include control-irrelevant a…
arXiv:2609.34792v2 Announce Type: replace Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VLA) policies often rely on the latest observation, and refreshing their visua…
arXiv:2609.39178v1 Announce Type: cross Abstract: Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understanding, and action generation in an end-to-end learning framework. However, since …
arXiv cs.CV
TIER_1English(EN)·Yanyan Zhang, Disheng Liu, Xinpeng Li, Chaoda Song, Mohsen Hariri, Debargha Ganguly, Wang Yang, Kai Ye, Bryce Grant, Vipin Chaudhary, Yu Yin·
arXiv:2609.38616v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models enable flexible action generation, their generalization across diverse environmental elements, including manipulated objects, destinations, and backgrounds, is limited by the lack of diver…
arXiv:2609.39915v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents offer a promising basis for this task, but selecting plausible local actions doe…
