Vision-Language-Action models for generalist robot control.
Jiaxin Shi, Xidong Zhang, Fucai Zhu et al.
We propose a 3D-thinking-guided co-training framework that enables vision-language-action (VLA) models to perform 3D spatial reasoning implicitly during action prediction.
Mozes Jacobs, Aiden Swann, Mathilde Papillon et al.
Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it?
Mathilde Kappel, Clémence Grislain, Mohamed Chetouani et al.
Vision-Language-Action (VLA) models have become a prominent paradigm for mapping multimodal inputs, including semantic instructions, visual observations of the scene, and proprioceptive observations, to robot actions.
Zachary Ravichandran, Jonathan Diller, Fernando Cladera et al.
Foundation models provide robots with the ability to interpret natural language and reason about environmental context, yet most language-conditioned policies assume that goals are well-specified and that task-relevant information is provided upfront via a prior map.
Ryo Terashima, Yuga Yano, Hakaru Tamukoh
In this study, we propose an adaptive question generation mechanism that addresses uncertainty arising from ambiguous instructions. Natural-language instructions for service robots often contain ambiguities.
Jianli Sun, Bin Tian, Qiyao Zhang et al.
Aerial manipulation systems have long suffered from representation coupling in end-to-end control, as platform-level Unmanned Aerial Vehicle (UAV) movement and end-effector-level arm manipulation differ substantially in action scale, dynamics, and control objectives.
Zuojin Tang, Haoyun Liu, Xinyuan Chang et al.
Vision-Language-Action (VLA) models map visual observations and language instructions to robot actions through learned latent representations.
Gokul Puthumanaillam, Tao Sun, Elie Aljalbout et al.
The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.
Tao Lin, Yikeng Chen, Qiwei Liang et al.
Layer pruning reduces the size and inference cost of vision-language-action (VLA) models, but selecting a deployable configuration requires deciding both which layers to remove and how to recover task performance.
Wenxuan Guo, Xiuwei Xu, Yichen Liu et al.
AwareVLN introduces selective self-aware reasoning for VLN agents, triggering explicit spatial and progress analysis only at uncertain waypoints to improve robustness and explainability.
Mengfei Zhao, Dihong Huang, Yikai Tang et al.
Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale because they rely on specialized hardware, centralized operators, or fixed task suites.
Wenbo Yu, Jifan Li, Wenke Xia et al.
While asynchronous execution enables VLA models to operate in real-time environments by predicting the next chunk during execution, it inevitably introduces boundary misalignment with the committed action stream.
Haoran Chen, Jingtian Ji, Samuel Wheeler et al.
Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise control actions in continuous space. Many action tokenizers learn the mapping between tokens and actions via a reconstruction objective.
Namiko Saito, Hiroshi Kera
Manipulation requires not only reasoning about the external environment, but also about the robot's physical condition.
Zhongxi Chen, Yifan Han, Yanming Shao et al.
Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation. However, dexterous manipulation remains chall
Xue Qin, Simin Luan, Cong Yang et al.
Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how closely they reproduce real-world contact dynamics.
Zhaoda Du, Michael Bowman, Xiaoli Zhang
Shared control often allocates robot authority based on confidence in inferred human intent, assuming reliable autonomous execution. When this assumption fails, high intent confidence can cause over-helping.
Aiden Swann, Mathilde Papillon, Mozes Jacobs et al.
Vision-language-action (VLA) models are a promising approach to general purpose robot manipulation.
Shutong Ding, Zhaoyang Liu, Yimiao Zhou et al.
Diffusion policies are increasingly used in robotic control and manipulation, vision-language-action models, and world-model-based agents. Their ability to represent multimodal action distributions offers rich opportunities for exploration in reinforcement learning (RL).
Ziyi Sun, Jingwen Chen, Yuxi Wang et al.
Recent advances in humanoid robotics have produced diverse skills through reinforcement learning, motion imitation, and generative modeling. Yet these capabilities remain siloed because they are built around incompatible representations, interfaces, and controllers.
Ci Zhang, Enfu Nan, Arman Akbari et al.
Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution.
Xilun Zhang, Maggie Wang, Erik Bauer et al.
Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the variety of situations a robot meets in real-world deployment.
Matteo Merler, Bowen Li, Josh Roy et al.
Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints.
Cong-Thanh Vu, Yen-Chen Liu
Precision pesticide spraying is essential for optimizing application efficiency and ensuring uniform chemical distribution.
Ruoyu Yao, Yusen Xie, Qingzhao Liu et al.
Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a significant challenge.
Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan et al.
Vision-language-action models (VLAs) are moving rapidly towards deployment as general-purpose manipulation policies, but we currently lack basic tools for understanding what these models represent internally or for monitoring them at runtime.
Zerui Kang, Yishen Lim, Zhouyou Gu et al.
An electromagnetic (EM) digital twin gives mobile robots wireless situational awareness but depends on material conductivities that change with the environment. Online calibration faces initialization sensitivity and measurement travel costs.
Thang Tran Viet, Thanh Nguyen Canh, Huy Uong Gia et al.
Human-robot interaction (HRI) enables intuitive and intelligent collaboration between humans and robots in real-world environments. This paper introduces a humanoid robot prototype designed as a flexible testbed for developing and integrating artificial intelligence (AI) modules in HRI tasks.
Yunchao Yao, Zhuxiu Xu, Tianqi Zhang et al.
Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across diverse interaction modes, sensory conditions, and robot embodiments.
Chenchao Sheng, Zhuang Jiang, Liuhaichen Yang et al.
Before deploying runtime recovery for a frozen vision-language-action (VLA) policy, one must establish that an intervention improves success beyond ordinary run-to-run variation and that its complexity adds value over a simple action.
Youngjun Jun, Kyumin Choi, Youngmin Kim et al.
Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control.
Kapalik Khanal, Biswash Khatiwada, Stephen Afrifa et al.
Changing a humanoid robot's manipulation policy should not require retraining the controller that maintains the robot's balance.
Hanchu Zhou, Dechen Gao, Hang Wang et al.
Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings.
Jusuk Lee, Seungjae Lee, Jonghun Shin et al.
Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recog
Junfeng Li, Junjie He, Zhide Zhong et al.
Vision-Language-Action (VLA) models have become a powerful paradigm for robot manipulation, but training a single generalist policy for heterogeneous robot embodiments remains an open problem. Existing methods have two main limitations.
Kairui Hu, Siyuan Hu, Fangzhou Hong et al.
Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time.
Devin Han, Hershraj Niranjani
Flow-based policies such as $\pi_0$ are trained on a fixed set of embodiments, and transferring them to new ones is an open problem.
ZhiYuan Feng, Zhuoshi Pan, Zhaolu Kang et al.
Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into subsequent decisions.
Sitan Huang, Grace Gao
Surface navigation on the Moon is subject to extreme illumination contrast and deployment-time perceptual disturbances.
Tsunehiko Tanaka, Matthew Stephenson, Alistair Macvicar et al.
Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. However, under partial observability, the availability of goal-relevant objects may be uncertain.
Shiyuan Yang, Borong Zhang, Jizheng Zhang et al.
We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation.
Haoran Pei, Mingrui Luo, Senbao Wang et al.
Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring components.
Pavel Bushuyeu, Yujin Chen, Anton Nikolaev et al.
Existing benchmarks evaluate tabletop manipulation, flat-floor household activity, or humanoid locomotion and manipulation as separate task groups; none scores vertical mobility and dexterous work on a fragile payload in one long-horizon episode.
Zekai Li, Jiaming Tang, Zhijian Liu
Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high inference latency and unstable asynchronous execution.
Chenhuan Liu, Yi Xu, Feng Wu et al.
Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world.
Zhengyu Tao, Xin Li, Xin Wang
Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, yet their reliance on visual perception limits robustness in contact-rich environments, where critical physical interaction states may not be visually observable.
Wenxuan Guo, Ziyuan Li, Meng Zhang et al.
GesVLA augments standard VLA models with gesture awareness, enabling robots to interpret verbal instructions alongside human hand gestures for disambiguated manipulation.
Yupeng Zheng, Xiang Li, Songen Gu et al.
Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native action and visual-prediction objectives may omit critical physical and task structure while retaining control-irrelevant visual redundancy.
Xiaosong Jia, Bowen Yang, Zuhao Ge et al.
Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Existing VLAs rely on end-to-end supervision to implicitly enable the action decoding process to learn task-relevant features.
Jinu Pahk, Jesoon Kang, Taegeon Park et al.
Vision-language-action policies benefit from geometric supervision, but current-frame geometry alone does not explicitly describe the changes associated with manipulation.
Zengjue Chen, Peidong Liu, Jiawei Li et al.
Generalist robot policies have demonstrated strong generalization across robotic manipulation tasks, yet their success rates remain limited in com- plex long-horizon scenarios.
Ryohei Kobayashi, Kosei Isomoto, Yuga Yano et al.
We propose a framework that transfers tacit human subjective criteria to robotic systems for the appropriate grasping of deformable objects. Achieving such behavior is challenging because a semantic gap exists between qualitative human expectations and quantitative robotic measurements.
Thomas Landeg, Thierry Tambe
Vision-Language-Action (VLA) models perform well on robotic manipulation, yet remain brittle once their own actions carry them into states their training data barely covers.
Andy Tang, William Chen, Andrew Wagenmaker et al.
Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve on challenging news tasks, we need a way to infer and invoke the appropriate actions from the policy's rich behavioral prior, especially when directly commanding the policy fails.
Yiqi Wang, Zhifeng Rao, Jiaqi Zhang et al.
Open robot policies increasingly follow two paradigms: vision-language-action models (VLAs) directly map observations and instructions to actions, whereas world-action models (WAMs) incorporate learned video or world dynamics into policy learning or action generation.
Zhuo Lin, Sirui Xu, Liuyu Bian et al.
We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attempts, and retaining what it learns, without retraining.
Tobias Schaffer, Mohab Elkhayat, Daniela Nicklas et al.
Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations of successful task execution.
Shuangyu Xie, Kaiyuan Chen, Muhammad Zubair Irshad et al.
KiRoSe segments robot demonstrations from compact kinematic tokens instead of raw multi-camera video, which the authors note is costly for multimodal models and quickly exhausts context windows.
Zeyu Lou, Yanhong Zeng, Yong Wang et al.
A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect.
Yongshuo Liu, Xu Gao, Morui Zhu et al.
We present LANTERN, a closed-loop benchmark for temporally grounded cooperative warnings.
Shichao Zhai, Shuhao Ye, Rong Xiong et al.
Object-goal navigation (ObjectNav) in multi-floor scenarios presents a challenge due to sparse rewards caused by long-horizon decision-making.
Sreejan Kumar, Marcelo Mattar, Lea Duncker
Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented as low-rank perturbations of a shared recurrent network, but leaves open how such a system is learned.
Zhixu Li, Keqian Tang, Litian Gong et al.
Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality.
Lee, Yumin, Ju, Hyoseok, Kim, Giseop
Long-term robot operation in evolving environments requires object-level understanding that persists across repeated revisits.
Ke Zhang, Danica J. Sutherland, Chao Liu
Training data variation, whether through designing a domain randomization (DR) scheme in simulation or curating demonstrations for imitation learning, is a primary lever for improving the robustness of robotic manipulation policies.
Yajie Li, Bozhou Zhang, Chun Gu et al.
Video foundation-models models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined futures for action execution remains challenging.
Aiden Swann, Mozes Jacobs, Mathilde Papillon et al.
Can better feature discovery improve control over robot behavior through internal interventions and training data? Recent work in vision and language models reveals multidimensional features, motivating block-sparse featurizers (BSFs), which represent each feature in a low-dimensional subspace.
Gengze Zhou, Yicong Hong, Jiazhao Zhang et al.
Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and decide.
Jack B. Jedlicki, Tanguy Dieudonn\'e, Heng Yang
Long-horizon manipulation often requires reasoning about state absent from the current view, such as a vanished object's location, temporal identity, or the contents of a shuffled container.
Chang Liu, Sibo Tian, Litian Gong et al.
Robotic disassembly of end-of-life (EoL) products requires robots to accommodate product variation, follow prerequisite sequences, and approach components precisely for contact-rich manipulation.
Sergey Arkhangelskiy
Real-world evaluation of vision-language-action (VLA) policies still rests on binary success rate at a fixed timeout with N <= 25 rollouts per condition, almost always without confidence intervals or
Aoran Jiao, Wenda Zhao, Hshmat Sahak et al.
Terrain assessment is a critical capability for off-road mobile robots, enabling safe and reliable navigation through unstructured and geometrically complex environments. Conventional geometry-based terrain assessment is fast to compute but often overly conservative in unstructured environments.
Yanchen Guan, Xingcheng Liu, Bin Rao et al.
End-to-end autonomous driving has evolved from camera-to-control regression toward planning-oriented systems that use structured representations, trajectory-level outputs, and increasingly realistic evaluation protocols.
Maria Attarian, Yifan Ruan, Claas Voelcker et al.
While Vision-Language-Action models have enabled impressive cross-task transfer in zero-shot settings, \emph{adaptation} methods are often necessary to achieve consistent performance on novel tasks.
Zhen Sun, Yongjian Guo, Haoran Sun et al.
A lightweight runtime verification layer that preemptively prunes unsafe VLA and world-model actions before they reach robot hardware, eliminating collision and droppage failures.
Xinyu Guo, Bin Xie, Wei Chai et al.
Vision-Language-Action (VLA) models have shown promise for generalizable robot control but struggle when adapting to new domains while preserving prior capabilities.
Shizuo Tian, Haodong Luo, Yutong Li et al.
Rapid adaptation to a new environment requires a robot to acquire useful knowledge about local objects, states, and interactions from limited experience.
Qiuyue Wang, Mingsheng Li, Jian Guan et al.
Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks,
Dogun Kim, Yongjae Lee, Joonhee Lim et al.
Recent Vision-Language-Action (VLA) models for autonomous driving have incorporated world modeling by predicting future driving scenes alongside driving actions, demonstrating strong planning performance.
Seunghun Lee, Kyuhwan Shim, Yeogyeong Song et al.
Existing vision-language-action (VLA) models benefit from large-scale vision-language pretraining, but tend to memorize training trajectories, limiting their ability to adapt learned interactions to new task and scene configurations.
Yen-Jen Wang, Haozhe Jiang, Shuying Deng et al.
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control.
Yuxuan Chen, Wanruo Zhang, Xiao Li
Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation. However, existing benchmarks mainly evaluate generalization on static manipulation tasks and largely overlook dynamic interaction scenarios.
Bince Qu, Wei Chen, Bo Zhang
The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world.
Zhenxuan Fan, Bo Zhang, Yutong Lin et al.
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation.
Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng et al.
Recent robot foundation models operate with single-step or short-history visuomotor context.
Xi Chen, Fengqi Hu, Zeyu Shen et al.
Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions.
Ruoxuan Feng, Yutong Chen, Ruihua Song et al.
Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we naturally interact with the environment by deciding what information is missing, how to acquire it, and when sufficient evidence has been obtained.
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong et al.
Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same reward under semantically equivalent goal descriptions. We show that current VLM reward models often violate this property.
Hongxin Zhang, Chunru Lin, Tsun-Hsuan Wang et al.
While Vision-Language-Action (VLA) models demonstrate impressive capabilities in robotic manipulation, their memoryless nature renders them brittle to test-time environment shifts, particularly hardware shifts caused by wear or imperfect calibration.
Gopi Krishna Erabati, Bjarne Johannsen, Angus Stewart et al.
Autonomous wheel-loader control requires joint reasoning over task semantics, egocentric vision, proprioception, and 3D scene geometry.
Wenhao Wang, Yanyan Li, Jiawei Yuan
Small language models (SLMs) have been increasingly adopted for onboard robot operation because they enable intelligent decision-making. However, existing approaches are mainly distillation-oriented and rely on enumerating representative task-solution pairs.
He Zhu, Lusen Zhao, Kwan Man Cheng et al.
Large-scale demonstrations have driven unprecedented progress in robot learning, yet collecting robot data through teleoperation is expensive and difficult to scale to diverse environments and long-horizon tasks.
Sofya Konstantinova, Miguel Altamirano Cabrera, Artem Lykov et al.
Vision-language-action (VLA) policies enable diverse robotic manipulation but can fail during execution without recognizing their own errors. Human observers provide complementary signals, as unexpected robot behavior can trigger rapid vocal, facial, or verbal reactions before failure is completed.
Pengteng Li, Weiyu Guo, He Zhang et al.
SOMA introduces an explicit spatial memory framework that enables VLA models to track and manipulate objects even after they leave the camera's field of view.
Maitrey Gramopadhye, Prakash Baskaran, Xiao Liu et al.
Effective human-robot collaboration in industrial settings requires robots to understand human intentions and assist with task planning, reducing workload.
Aditya Dutta, Joon-Seok Kim
Automated fulfillment warehouses must continuously assign and execute pickup-and-delivery work while avoiding congestion.
Hiago Sodre, Sebastian Barcelona, Vincent Sandin et al.
Integrating Vision-Language Models (VLMs) into autonomous UAV navigation enables high-level semantic reasoning but introduces critical temporal bottlenecks that can destabilize flight control.
Rhythm Syed, Jean Mercat, Sedrick Keh et al.
Vision-language-action models (VLAs) inherit strong semantic grounding from pretrained vision-language backbones but are typically optimized for predicting actions rather than future observations. They can see and act, but they do not imagine the future before acting.
Mousumi Das, Aditeya Prajapati, Abrar Anwar et al.
Robot manipulation systems using Vision-Language-Action (VLA) model backbones typically use just one VLA for task execution. However, individual VLAs do not perform well across different task states and environments.
Tingcong Liu, Aye Phyu Phyu Aung, Junjie Xiong et al.
Soft and continuum robots enable manipulation through distributed body deformation and contact, yet translating language and visual context into executable whole-body actuation remains a fundamental challenge.
Guangxin Zhao, Yiran Hu, Yuan Cao et al.
Existing LLM-driven robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focused.
Vivek Chavan, Yahuan Shi, Oliver Heimann et al.
Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task state, dependency-aware reasoning, conditional decisions, and reliable grounding.
Fan Pu, Keshu Wu, Jiwan Jiang et al.
Real-world Vision-Language Navigation (VLN) requires agents to act under partial observability, where map structure, semantic cues, and target locations may be incomplete or incorrectly inferred by foundation models.
Masato Kobayashi, Takeru Tsunoori
Underwater visuomotor policy learning has focused primarily on single manipulators, while bimanual imitation learning has been studied largely in air.
Ralf Römer, Maximilian Seeliger, Saida Liu et al.
Quantifies epistemic uncertainty in flow-matching VLAs using velocity-field disagreement (VFD) across a small ensemble, enabling failure detection at deployment and sample-efficient active fine-tuning (SAVE).
Junjie Lu, Xinyao Qin, Yuhua Jiang et al.
Diffusion-based vision-language-action (VLA) models have emerged as strong priors for robotic manipulation, yet adapting them to real-world distributions remains challenging.
Wei Li, Rui Shao, Jie He et al.
Recent advances in Vision-Language-Action (VLA) models have improved robotic manipulation, yet observation-to-action learning remains limited by a fundamental transition realizability gap, manifested in three tightly coupled problems: (i) Transition ambiguity.
Jiayi Chen, Wenxuan Song, Jingbo Wang et al.
Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in world dynamics.
Boyao Han, Chen Shi, Jingjing Qian et al.
Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in camera count or pose during deployment.
Mert Albaba, Jens Beißwenger, Anna Manasyan et al.
Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the robot keeps its balance, which makes joint-level actions hard to learn.
Chang Song, Bin Qian, Yan Feng et al.
Long-horizon robot manipulation with Vision-Language-Action (VLA) policies remains vulnerable to execution-time deviations, as final task success provides little information for diagnosing and correcting failures caused by action noise, object displacement, or goal misalignment.
Jiuyi Xu, Qing Jin, Meida Chen et al.
Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, numerical format, and calibration.
Jiabin Lou, Haopeng Wang, Yuanshuai Wang et al.
Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions.
Vivek Chavan, Pengtao Xie, Yahuan Shi et al.
Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced.
Junxiang Wang, Yuchen Liu, Yi Wu et al.
Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests.
Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu et al.
Shortcut learning is a prevalent issue in robot learning. The limited diversity of robot demonstration datasets can mislead policies into exploiting spurious correlations between tasks and irrelevant features, such as viewpoint or background.
Victoria Smelova, Daniil Kazachkov, Georgiy Kazantsev et al.
Long-horizon, multi-stage Vision-Language-Action (VLA) policies often require visual information that is no longer present in the current observation. Retaining the complete observation history is computationally expensive and highly redundant, motivating selective visual memory.
Jie He, Wei Li, Junwen Tong et al.
Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source.
Zhe Li, Zhenzhe Zhang, Yangyang Wei et al.
Humanoid household tasks often require concurrent loco-manipulation, where the robot must move, adjust posture, maintain balance, and manipulate objects as a single coordinated behavior.
NVIDIA, :, Johan Bjorck et al.
General-purpose robots need a versatile body and an intelligent mind. Recent advancements in humanoid robots have shown great promise as a hardware platform for building generalist autonomy in the human world.
Haoran Jiang, Jin Chen, Qingwen Bu et al.
Humanoid robots require precise locomotion and dexterous manipulation to perform challenging loco-manipulation tasks. Yet existing approaches, modular or end-to-end, are deficient in manipulation-aware locomotion.
Karl Pertsch, Oliver Groth, Jonas Frey et al.
π0 is a 3.5B-parameter VLA flow model from Physical Intelligence that achieves state-of-the-art general robot manipulation by mixing online RL with high-quality human demonstrations, available as an open-source PyTorch implementation.
Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti et al.
A 7B-parameter open-source Vision-Language-Action model pre-trained on 970k real-world robot demonstrations, achieving strong generalization across robots and tasks.
Anthony Brohan, Yevgen Chebotar, Chelsea Finn et al.
RT-1 is a 35M-parameter transformer trained on 130K robot demonstrations that generalizes to new tasks, objects, and environments, forming the foundation for Google's RT-2 and RT-X line of VLA models.
Wei Xu, Yixi Cai, Dongjiao He et al.
A tightly-coupled LiDAR-inertial odometry system with incremental kd-tree mapping, enabling real-time state estimation for UAVs and mobile robots.
Read these papers in order to build expertise in VLA.
Jiaxin Shi, Xidong Zhang et al. · 2026
Mozes Jacobs, Aiden Swann et al. · 2026
Mathilde Kappel, Clémence Grislain et al. · 2026
Zachary Ravichandran, Jonathan Diller et al. · 2026
Ryo Terashima, Yuga Yano et al. · 2026
Jianli Sun, Bin Tian et al. · 2026
…and 119 more papers.
