Vision-Language-Action Models

Also known as VLA

Follow this topic Ask about this topic

Latest papers 1,128

249 papers in the last four weeks, up 144% on the four weeks before. 1.5% of all new papers.

Mar 13, 2026

PVI: Plug-in Visual Injection for Vision-Language-Action Models

VLA architectures that pair a pretrained VLM with a flow-matching action expert have emerged as a strong paradigm for language-conditioned manipulation. Yet the VLM, optimized for semantic abstraction and typically conditioned on static visual observations, tends to attenuate fine-grained geometric cues and often lacks explicit temporal evidence for the action expert. Prior work mitigates this by injecting auxiliary visual features, but existing approaches either focus on static spatial representations or require substantial architectural modifications to accommodate temporal inputs, leaving temporal information underexplored. We propose Plug-in Visual Injection (PVI), a lightweight, encoder-agnostic module that attaches to a pretrained action expert and injects auxiliary visual representations via zero-initialized residual pathways, preserving pretrained behavior with only single-stage fine-tuning. Using PVI, we obtain consistent gains over the base policy and a range of competitive alternative injection strategies, and our controlled study shows that temporal video features (V-JEPA2) outperform strong static image features (DINOv2), with the largest gains on multi-phase tasks requiring state tracking and coordination. Real-robot experiments on long-horizon bimanual cloth folding further demonstrate the practicality of PVI beyond simulation.

Zezhou Zhang, Songxin Zhang, Xiao Xiong +8

Lionrock AI Lab, China Merchants Group, Hong Kong, China

Vision-Language-Action Models VLMs for Robotics Robotic Manipulation

Mar 13, 2026

AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulation

Since current Vision-Language-Action (VLA) systems suffer from limited spatial perception and the absence of memory throughout manipulation, we investigate visual anchors as a means to enhance spatial and temporal reasoning within VLA policies for robotic manipulation. Conventional VLAs generate actions by conditioning on a single current frame together with a language instruction. However, since the frame is encoded as a 2D image, it does not contain detailed spatial information, and the VLA similarly lacks any means to incorporate past context. As a result, it frequently forgets objects under occlusion and becomes spatially disoriented during the manipulation process. Thus, we propose AnchorVLA4D, a simple spatial-temporal VLA that augments the visual input with an anchor image to preserve the initial scene context throughout execution, and adds a lightweight spatial encoder that jointly processes the anchor and current frames to expose geometric relationships within an episode. Built on a Qwen2.5-VL backbone with a diffusion-based action head, AnchorVLA4D requires no additional sensing modalities (e.g., depth or point clouds) and introduces negligible inference overhead. Combining anchoring with a frozen pretrained spatial encoder yields further gains, realizing a 13.6% improvement on the Simpler WidowX benchmark and confirming the approach on real-world tasks, where it achieved an average success rate of 80%.

Juan Zhu, Zhanying Shao, Xiaoqi Li +4

PrimeBot · School of Computer Science, Peking University

Vision-Language-Action Models Language-Conditioned Robot Manipulation Memory-Augmented VLMs

Mar 13, 2026

Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy

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 actions conditioned on that chain. The works introducing this design offer the reasoning chain as an oversight interface: text a person can read and edit to correct the policy. What an edited reasoning chain does to the policy's motor actions, whether it repairs them or corrupts them, has so far been measured only in part. We measure both directions, repair and corruption, with our deterministic entity swap applied to the instruction the policy receives and to the reasoning chain it generates. A forty-task observed backdrop across all four LIBERO simulation suites reveals that the cost of corrupting the reasoning chain concentrates where language alone determines the goal. There, on LIBERO-Goal, we run the counterfactual intervention with DeepThinkVLA, chosen because its reasoning chain is exposed as plain text. The policy receives a corrupted instruction, but its reasoning chain is replaced by the one it generates when that instruction is clean. This counterfactually correct reasoning chain recovers 47.8 pp of the lost success, our pre-registered confirmatory test. Had the chain merely restated what the camera image already determines, the replacement could have changed nothing. Instead, all 10 tasks move in the predicted direction, though success falls short of the clean runs by 38.0 pp, a gap we had predicted at 5-15 pp. The reasoning chain is therefore a working control surface: text written into it moves the robot, repairing behaviour when the text is right and corrupting it when the text is wrong. Whether to expose such a control surface is a deployment tradeoff, and part of it can now be measured.

Tuan Duong Trinh, Basim Azam, Mohammed Ishaq Ansari +2

University of Melbourne Parkville, VIC, Australia

Language-Conditioned Robot Manipulation Vision-Language-Action Models Causal Interventions in Language Models Inference-Time Intervention Reasoning for VLA Models

Mar 13, 2026

TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation

Vision-Language-Action (VLA) models have demonstrated significant advantages in robotic manipulation. However, their reliance on vision and language often leads to suboptimal performance in tasks involving visual occlusion, fine-grained manipulation, and physical contact. To address these challenges, we propose TacVLA, a fine-tuned VLA model by incorporating tactile modalities into the transformer-based policy to enhance fine-grained manipulation capabilities. Specifically, we introduce a contact-aware gating mechanism that selectively activates tactile tokens only when contact is detected, enabling adaptive multimodal fusion while avoiding irrelevant tactile interference. The fused visual, language, and tactile tokens are jointly processed within the transformer architecture to strengthen cross-modal grounding during contact-rich interaction. Extensive experiments on constraint-locked disassembly, in-box picking and robustness evaluations demonstrate that TacVLA outperforms baselines, %including existing VLA models and diffusion policies, improving the performance by averaging 20% success rate in disassembly and 60% in in-box picking, achieving a 2.1

\times

improvement under visual occlusion, and showing recovery behavior under human disturbance. Videos are available at https://sites.google.com/view/tacvla.

Kaidi Zhang, Heng Zhang, Zhengtong Xu +7

Kaidi, Heng, Zhengtong, Zhiyuan, Prince, Xiang, Xiaojing, Yuhao, and Yu are with the Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA · Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genova, Italy. · Ph.D. program of national interest in Robotics and Intelligent Machines (DRIM) and Università di Genova, Genoa, Italy. +1

Contact-Rich Robotic Manipulation Robotic Manipulation Vision-Language-Action Models Tactile Sensing for Robotic Manipulation

Mar 12, 2026

SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics

Active perception and manipulation are crucial for robots to interact with complex scenes. Existing methods struggle to unify semantic-driven active perception with robust, viewpoint-invariant execution. We propose SaPaVe, an end-to-end framework that jointly learns these capabilities in a data-efficient manner. Our approach decouples camera and manipulation actions rather than placing them in a shared action space, and follows a bottom-up training strategy: we first train semantic camera control on a large-scale dataset, then jointly optimize both action types using hybrid data. To support this framework, we introduce ActiveViewPose-200K, a dataset of 200k image-language-camera movement pairs for semantic camera movement learning, and a 3D geometry-aware module that improves execution robustness under dynamic viewpoints. We also present ActiveManip-Bench, the first benchmark for evaluating active manipulation beyond fixed-view settings. Extensive experiments in both simulation and real-world environments show that SaPaVe outperforms recent vision-language-action models such as GR00T N1 and

π_0

, achieving up to 31.25% higher success rates in real-world tasks. These results show that tightly coupled perception and execution, when trained with decoupled yet coordinated strategies, enable efficient and generalizable active manipulation. Project page: https://lmzpai.github.io/SaPaVe

Mengzhen Liu, Enshen Zhou, Cheng Chi +6

State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Academy of Artificial Intelligence · School of Software, Beihang University

Active Vision for Robot Manipulation Robotic Manipulation Vision-Language-Action Models Data-Efficient Robot Learning Robot Manipulation Benchmarks

Mar 11, 2026

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

We propose DynVLA, a driving VLA model that introduces a new CoT paradigm termed Dynamics CoT. DynVLA forecasts compact world dynamics before action generation, enabling more informed and physically grounded decision-making. To obtain compact dynamics representations, DynVLA introduces a Dynamics Tokenizer that compresses future evolution into a small set of dynamics tokens. Considering the rich environment dynamics in interaction-intensive driving scenarios, DynVLA decouples ego-centric and environment-centric dynamics, yielding more accurate world dynamics modeling. We then train DynVLA to generate dynamics tokens before actions through SFT and RFT, improving decision quality while maintaining latency-efficient inference. Compared to Textual CoT, which lacks fine-grained spatiotemporal understanding, and Visual CoT, which introduces substantial redundancy due to dense image prediction, Dynamics CoT captures the evolution of the world in a compact, interpretable, and efficient form. Extensive experiments on NAVSIM, Bench2Drive, and a large-scale in-house dataset demonstrate that DynVLA consistently outperforms Textual CoT and Visual CoT methods, validating the effectiveness and practical value of Dynamics CoT. Project Page: https://yaoyao-jpg.github.io/dynvla.

Shuyao Shang, Bing Zhan, Yunfei Yan +9

NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA) · Yinwang Intelligent Technology Co. Ltd.

Autonomous Driving Vision-Language-Action Models Reasoning for VLA Models World Models for Autonomous Driving World Models Efficient VLA Model Inference

Mar 11, 2026

FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model

Predictive foresight is important to intelligent embodied agents. Since the motor execution of a robot is intrinsically constrained by its visual perception of environmental geometry, effectively anticipating the future requires capturing this tightly coupled visuomotor interplay. While recent vision-language-action models attempt to incorporate future guidance, they struggle with this joint modeling. Existing explicit methods divert capacity to task-irrelevant visual details, whereas implicit methods relying on sparse frame pairs disrupt temporal continuity. By heavily relying on visual reconstruction, these methods become visually dominated, entangling static scene context with dynamic action intent. We argue that effective joint visuomotor predictive modeling requires both temporal continuity and visually-conditioned supervision decoupling. To this end, we propose FutureVLA, featuring a novel Joint Visuomotor Predictive Architecture. FutureVLA is designed to extract joint visuomotor embeddings by first decoupling visual and motor information, and then jointly encoding generalized physical priors. Specifically, in the pretraining stage, we leverage heterogeneous manipulation datasets and introduce a Joint Visuomotor Gating mechanism to structurally separate visual state preservation from temporal action modeling. It allows the motor stream to focus on continuous physical dynamics while explicitly querying visual tokens for environmental constraints, yielding highly generalizable joint visuomotor embeddings. Subsequently, in the post-training stage, we employ a latent embeddings alignment strategy, enabling diverse downstream VLA models to internalize these temporal priors without modifying their inference architectures. Extensive experiments demonstrate that FutureVLA consistently improves VLA frameworks.

Xiaoxu Xu, Hao Li, Jinhui Ye +7

Beihang University. · Shanghai Artificial Intelligence Laboratory. · University of Science and Technology of China. +1

Vision-Language-Action Models Visuomotor Policy Learning Robotic Manipulation Motion Representation Learning

Mar 11, 2026

DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either prune or merge tokens uniformly, degrading the spatial reasoning essential for robotic control. We present DepthCache, a training-free framework that leverages depth as a structural prior for visual token compression. It partitions observations into depth-based regions and applies spatially differentiated merge ratios, preserving the near-field workspace while compressing the distant background. To exploit temporal redundancy, DepthCache distributes the merging process across consecutive frames, ensuring consistent representations while reducing per-step computation. A motion-adaptive pipeline further optimizes auxiliary view compression based on end-effector dynamics. The framework requires no model modification, generalizing across diverse VLA architectures. On the LIBERO benchmark, DepthCache achieves up to 1.28x inference speedup with less than 1% average success rate degradation across three VLA models (pi_0.5, OpenVLA, GR00T), whereas pruning and merging baselines incur 4--24% degradation at comparable compression. Real-world experiments on a physical manipulator demonstrate that DepthCache enables faster task throughput and more responsive closed-loop control in latency-sensitive scenarios.

Yuquan Li, Lianjie Ma, Han Ding +1

School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China. · School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China.

Efficient VLA Model Inference Visual Token Compression Vision-Language-Action Models Visual Token Merging VLMs for Robotics

Mar 11, 2026

World2Act: Latent Action Post-Training from World Model Dynamics

World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training methods rely on pixel-space supervision, making policies sensitive to visual artifacts introduced by imperfect WM rollouts. We present World2Act, a latent-space post-training framework that transfers WM dynamics to the VLA policy without pixel-space supervision. World2Act operates in two stages: 1) it induces a shared video-action latent space by contrastively aligning WM-dynamics latents with action embeddings, and 2) it post-trains the VLA by guiding policy action representations toward WM-imagined dynamics rather than decoded pixels. Built on GR00T-N1.6, World2Act delivers absolute success-rate gains of up to +2.5% on simulation benchmarks (RoboCasa, LIBERO, Bridge-SIMPLER) and +6.7% on a real robot over finetuned VLA baselines. Notably, it outperforms pixel-space WM supervision by up to +6.0%, including on LIBERO where pixel supervision degrades the baseline, suggesting that latent WM dynamics offer a more stable WM-based post-training alternative to pixel-space transfer.

An Dinh Vuong, Tuan Van Vo, Abdullah Sohail +6

MBZUAI

Vision-Language-Action Models VLMs for Robotics Latent Action Learning

Mar 11, 2026

Overcoming Visual Clutter in Vision Language Action Models via Concept-Gated Visual Distillation

Vision-Language-Action (VLA) models demonstrate impressive zero-shot generalization but frequently suffer from a "Precision-Reasoning Gap" in cluttered environments. This failure is driven by background-induced feature dilution, where high-frequency semantic noise corrupts the geometric grounding required for precise manipulation. To bridge this gap, we propose Concept-Gated Visual Distillation (CGVD), a training-free, model-agnostic inference framework that stabilizes VLA policies. CGVD operates by parsing instructions into safe and distractor sets, utilizing a two-layer target refinement process--combining cross-validation and spatial disambiguation--to explicitly penalize false positives and isolate genuine manipulation targets. We then process the scene via Fourier-based inpainting, generating a clean observation that actively suppresses semantic distractors while preserving critical spatial geometry and visual proprioception. Extensive evaluations in highly cluttered manipulation tasks demonstrate that CGVD prevents performance collapse. In environments with dense semantic distractors, our method significantly outperforms state-of-the-art baselines, achieving a 77.5% success rate compared to the baseline's 43.0%. By enforcing strict attribute adherence, CGVD establishes inference-time visual distillation as a critical prerequisite for robust robotic manipulation in the clutter.

Sangmim Song, Sarath Kodagoda, Marc Carmichael +1

University of Technology Sydney, NSW, Australia · Western Sydney University, NSW, Australia

Vision-Language-Action Models Robustness of VLA Models Robotic Manipulation Language-Conditioned Robot Manipulation

Mar 10, 2026

SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich Disassembly

Disassembly automation has long been pursued to address the growing demand for efficient and proper recovery of valuable components from the end-of-life (EoL) electronic products. Existing approaches have demonstrated promising and regimented performance by decomposing the disassembly process into different subtasks. However, each subtask typically requires extensive data preparation, model training, and system management. Moreover, these approaches are often task- and component-specific, making them poorly suited to handle the variability and uncertainty of EoL products and limiting their generalization capabilities. All these factors restrict the practical deployment of current robotic disassembly systems and leave them highly reliant on human labor. With the recent development of foundation models in robotics, vision-language-action (VLA) models have shown impressive performance on standard robotic manipulation tasks, but their applicability to complex, contact-rich, and long-horizon industrial practices like disassembly, which requires sequential and precise manipulation, remains limited. To address this challenge, we propose SELF-VLA, an agentic VLA framework that integrates explicit disassembly skills. Experimental studies demonstrate that our framework significantly outperforms current state-of-the-art end-to-end VLA models on two contact-rich disassembly tasks. The video illustration can be found via https://zh.engr.tamu.edu/wp-content/uploads/sites/310/2026/03/IROS-VLA-Video.mp4.

Chang Liu, Sibo Tian, Xiao Liang +1

J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA. · Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, TX 77843, USA.

Vision-Language-Action Models Contact-Rich Robotic Manipulation Robotic Manipulation Long-Horizon Robotic Manipulation

Mar 10, 2026

Cross-Hand Latent Representation for Vision-Language-Action Models

Dexterous manipulation is essential for real-world robot autonomy, mirroring the central role of human hand coordination in daily activity. Humans rely on rich multimodal perception--vision, sound, and language-guided intent--to perform dexterous actions, motivating vision-based, language-conditioned manipulation systems for robots. However, training reliable vision-language-action (VLA) models for dexterous manipulation requires large-scale demonstrations across many robotic hands. In addition, as new dexterous embodiments appear rapidly, collecting data for each becomes costly and impractical, creating a need for scalable cross-embodiment learning. We introduce XL-VLA, a vision-language-action framework integrated with a unified latent action space shared across diverse dexterous hands. This embodiment-invariant latent space is directly pluggable into standard VLA architectures, enabling seamless cross-embodiment training and efficient reuse of both existing and newly collected data. Experimental results demonstrate that XL-VLA consistently outperforms baseline VLA models operating in raw joint spaces, establishing it as an effective solution for scalable cross-embodiment dexterous manipulation.

Guangqi Jiang, Yutong Liang, Jianglong Ye +6

UC San Diego · Amazon FAR · UC Berkeley

Robotic Manipulation Cross-Embodiment Robot Learning Vision-Language-Action Models Language-Conditioned Robot Manipulation Latent Action Learning

Mar 10, 2026

AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models

We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refreshable vision-language prefixes. In contrast to existing Vision-Language-Action (VLA) models and diffusion policies that reset temporal context with each new observation and predict actions reactively, our Action Expert maintains its own history through a long-lived memory and is inherently context-aware. This structure addresses the frequency mismatch between fast control and slow reasoning, enabling efficient independent pretraining of kinematic syntax and modular integration with heavy perception backbones, naturally ensuring spatio-temporally consistent action generation across frames. To synchronize these asynchronous hybrid V-L-A modalities, we utilize a re-anchoring mechanism that mathematically accounts for perception staleness during both training and inference. Experiments on simulated and real-robot manipulation tasks demonstrate that the proposed method can effectively replace traditional chunk-based action heads for both specialist and generalist policies. AR-VLA exhibits superior history awareness and substantially smoother action trajectories while maintaining or exceeding the task success rates of state-of-the-art reactive VLAs. Overall, our work introduces a scalable, context-aware action generation schema that provides a robust structural foundation for training effective robotic policies. Code and Videos available at https://arvla.insait.ai

Yutong Hu, Jan-Nico Zaech, Nikolay Nikolov +6

∗INSAIT, Sofia University “St. Kliment Ohridski” · †KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics · ‡KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images

Vision-Language-Action Models Autoregressive Generation Robotic Manipulation

Mar 10, 2026

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

Vision-Language-Action (VLA) models are formulated to ground instructions in visual context and generate action sequences for robotic manipulation. Despite recent progress, VLA models still face structure-blind backbones, backbone-bound generalization, and flat single-objective optimization. To address these challenges, we propose a novel Neuro-Symbolic Vision-Language-Action (NS-VLA) framework. It introduces a Neuro-Symbolic Encoder for plan-constrained primitive inference, a Neuro-Symbolic Solver that conditions a backbone-agnostic policy on the active primitive, and Hierarchical Joint Policy Optimization with reward-granularity matching. Experiments on robotic manipulation benchmarks demonstrate that NS-VLA outperforms previous methods in both one-shot training and data-perturbed settings, while simultaneously exhibiting superior zero-shot generalizability and expanded exploration space. Our code is publicly available.

Ziyue Zhu, Shangyang Wu, Shuai Zhao +8

Beijing University of Posts and Telecommunications · Nanyang Technological University

Vision-Language-Action Models Robotic Manipulation Neurosymbolic Learning

Mar 10, 2026

StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving

Vision Language Models (VLMs) bridge visual perception and linguistic reasoning. In Autonomous Driving (AD), this synergy has enabled Vision Language Action (VLA) models, which translate high-level multimodal understanding into driving behaviors, typically represented as future trajectories. However, existing VLA models mainly generate generic collision-free trajectories. Beyond collision avoidance, adapting to diverse driving styles (e.g., sporty, comfortable) is essential for personalized driving. Moreover, many methods treat trajectory generation as naive token prediction, which can produce kinematically infeasible actions. To address these limitations, we present StyleVLA, a physics-informed VLA framework for generating diverse and physically plausible driving behaviors. We introduce a hybrid loss that combines a kinematic consistency constraint with a continuous regression head to improve trajectory feasibility. To train StyleVLA, built on Qwen3-VL-4B, we construct a large-scale instruction dataset with over 1.2k scenarios, 76k Bird's Eye View (BEV) samples, and 42k First Person View (FPV) samples, with ground-truth trajectories for five driving styles and natural-language instructions. Experiments show that our 4B-parameter StyleVLA significantly outperforms proprietary models (e.g., Gemini-3-Pro) and state-of-the-art VLA models. Using a composite driving score measuring success rate, physical feasibility, and style adherence, StyleVLA achieves 0.55 on BEV and 0.51 on FPV, versus 0.32 and 0.35 for Gemini-3-Pro. These results show that a specialized, physics-informed, lightweight model can surpass closed-source models on domain-specific tasks.

Yuan Gao, Dengyuan Hua, Mattia Piccinini +4

Y. Gao, D. Hua, M. Piccinini, F. Schäfer, K. Moller, J. Betz are with the Professorship of Autonomous Vehicle Systems, TUM School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI) · L. Li is with the School of Mechanical and Aerospace Engineering, Nanyang Technological University

Autonomous Driving Vision-Language-Action Models Autonomous Driving Planning

Mar 10, 2026

CORAL: Scalable Multi-Task Robot Learning via LoRA Experts

Deploying Vision-Language-Action (VLA) models in real-world robotics exposes a core multi-task learning challenge: reconciling task interference in multi-task robotic learning. When multiple tasks are jointly fine-tuned in a single stage, gradients from different tasks can conflict, causing negative transfer and reducing per-task performance. Yet maintaining a separate full checkpoint per task is often storage- and deployment-prohibitive. To address this dilemma, we present CORAL, a backbone- and embodiment-agnostic framework designed primarily to mitigate multi-task interference while remaining naturally extensible to a continuous stream of new tasks. CORAL freezes a single pre-trained VLA backbone and attaches one lightweight Low-Rank Adaptation (LoRA) expert per task; at runtime, a dynamic inference engine (the CORAL Manager) routes language instructions to the appropriate expert and swaps experts on the fly with zero inference overhead. This strict parameter isolation avoids complex gating networks and prevents parameter-level cross-task interference by construction; as an added capability, it also enables sequentially introducing new tasks without parameter overwriting caused by catastrophic forgetting. We validate CORAL on a real-world Galaxea R1 dual-arm mobile manipulator and three simulation benchmarks (LIBERO, WidowX, Google Robot), where CORAL overcomes fine-grained instructional ambiguity and substantially outperforms joint training, yielding a practical and scalable system for lifelong multi-task robot learning. Website: https://frontierrobo.github.io/CORAL

Yuankai Luo, Woping Chen, Tong Liang +1

Frontier Robotics

Robot Learning Continual Robot Learning Vision-Language-Action Models Negative Transfer

Mar 10, 2026

See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation

Measurement of task progress through explicit, actionable milestones is critical for robust robotic manipulation. This progress awareness enables a model to ground its current task status, anticipate verifiable intermediate states, and detect and recover from failures when progress stalls. To embody this capability, we introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework that dynamically grounds language instructions into a sequence of spatial subgoals. SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure by monitoring progress against the expected sequence. This closed-loop approach enables robust error correction without requiring additional training data or auxiliary models. Extensive experiments demonstrate the framework's effectiveness, generalization and robustness: SPR outperforms the MolmoAct baseline by 5% on the LIBERO benchmark. On the challenging LIBERO-Plus benchmark with unseen instructions and initial states, SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA, demonstrating superior out-of-distribution robustness.

Tingjun Dai, Mingfei Han, Tingwen Du +6

School of Information Science and Technology, University of Science and Technology of China, Anhui, China. · University of Technology Sydney, Ultimo, NSW, Australia. · Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates. +3

Vision-Language-Action Models Language-Conditioned Robot Manipulation Robustness of VLA Models Robot Failure Recovery Instruction Generalization in VLA Models

Mar 10, 2026

DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation

While Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities in robotic manipulation, deploying them on specific and complex downstream tasks still demands effective post-training. In parallel, Human-in-the-Loop (HiL) learning has proven to be a powerful mechanism for refining robot policies. However, extending this paradigm to dexterous manipulation remains challenging: multi-finger control is high-dimensional, contact-intensive, and exhibits execution distributions that differ markedly from standard arm motions, leaving existing dexterous VLA systems limited in reliability and adaptability. We present DexHiL, the first integrated arm-hand human-in-the-loop framework for dexterous VLA models, enabling coordinated interventions over the arm and the dexterous hand within a single system. DexHiL introduces an intervention-aware data sampling strategy that prioritizes corrective segments for post-training, alongside a lightweight teleoperation interface that supports instantaneous human corrections during execution. Real-robot experiments demonstrate that DexHiL serves as an effective post-training framework, yielding a substantial performance leap, outperforming standard offline-only fine-tuning baselines by an average of 25% in success rates across distinct tasks. Project page: https://chenzhongxi-sjtu.github.io/dexhil/

Yifan Han, Zhongxi Chen, Yuxuan Zhao +5

CASIA · SJTU · Shanghai AI Laboratory

Robotic Manipulation Robot Learning Vision-Language-Action Models

Mar 10, 2026

GST-VLA: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action Models

VLA models encode visual observations as 2D patch tokens with no intrinsic geometric structure. We introduce GST-VLA with two contributions. First, the Gaussian Spatial Tokenizer (GST) converts frozen dense depth and frozen semantic patch features into

N_g{=}128

anisotropic 3D Gaussian primitives, each parameterized by a metric residual mean

μ\in \mathbb{R}^3

, log-scale covariance

\log σ\in \mathbb{R}^3

, and learned opacity

α\in (0,1)

. The covariance eigenstructure encodes local surface orientation, and opacity provides per-primitive geometric confidence, both inaccessible from scalar depth. Spatial attention pooling with learned queries concentrates the fixed token budget on geometrically salient regions rather than distributing uniformly. Second, 3D Depth-Aware Chain-of-Thought (DA-CoT) reasoning supervises four structured intermediate spatial thoughts, covering 3D object grounding, grasp affordance contact geometry, pairwise metric distances, and coarse SE(3) waypoints, as explicit generation targets in the training loss. A cross-attention sublayer at every VLM transformer block provides direct access to the raw 256-primitive Gaussian field during DA-CoT generation. A 300M-parameter flow-matching action expert with mixture-of-experts feedforward sublayers decodes 7-DoF delta action chunks via conditional ODE integration, conditioned on both VLM hidden states and DA-CoT outputs through dual cross-attention. Trained with composite

\mathcal{L}_\mathrm{flow} + \mathcal{L}_\mathrm{CoT} + \mathcal{L}_\mathrm{depth}

across three progressive stages, GST-VLA achieves 96.4% on LIBERO (+2.0%), and 80.2% on SimplerEnv (+5.4%). Ablations isolate the contribution of each GST component, each DA-CoT thought, and each training stage, confirming independent and synergistic gains concentrated on precision demanding tasks.

Md Selim Sarowar, Omer Tariq, Sungho Kim

Yeungnam University · Korea Advanced Institute of Science and Technology, KAIST

Vision-Language-Action Models VLMs for Robotics Visual Tokenization Reasoning for VLA Models 3D Visual Grounding

Mar 9, 2026

OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies

Vision-language-action(VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on more complex tasks, such as those requiring complex spatial or semantic understanding, manipulation in clutter, or precise manipulation. We propose OMNIGUIDE, a flexible framework that improves VLA performance on such tasks by leveraging arbitrary sources of guidance, such as 3D foundation models, semantic-reasoning VLMs, and human pose models. We show how many kinds of guidance can be naturally expressed as differentiable energy functions with task-specific attractors and repellers located in 3D space, that influence the sampling of VLA actions. In this way, OMNIGUIDE enables guidance sources with complementary task-relevant strengths to improve a VLA model's performance on challenging tasks. Extensive experiments in both simulation and real-world environments, across diverse sources of guidance, demonstrate that OMNIGUIDE enhances the performance of state-of-the-art generalist policies (e.g.,

π_{0.5}

, GR00T N1.6) significantly across success and safety rates. Critically, our unified framework matches or surpasses the performance of prior methods designed to incorporate specific sources of guidance into VLA policies. Project Page: this ; url

Yunzhou Song, Long Le, Yong-Hyun Park +7

University of Pennsylvania

Robot Policy Learning Vision-Language-Action Models Robotic Manipulation

Mar 9, 2026

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component for effective control. However, current paradigms predominantly rely on coarse, high-level task instructions during supervised fine-tuning. This instruction grounding gap leaves models without explicit intermediate guidance, leading to severe compounding errors in long-horizon tasks. Therefore, bridging this instruction gap and providing scalable post-training for VLA models is urgent. To tackle this problem, we propose \method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline. Our framework leverages a large language model to decompose high-level demonstrations into fine-grained atomic subtasks. This approach utilizes a pretrained predictive world model to score candidate action chunks against subtask goals in the latent space, mitigating error accumulation while significantly improving long-horizon robustness. Furthermore, this approach enables highly efficient Group Relative Policy Optimization without the prohibitive expenses associated with online rollouts on physical robots. Extensive simulations validate that our AtomVLA maintains strong robustness under perturbations. When evaluated against fundamental baseline models, it achieves an average success rate of 97.0% on the LIBERO benchmark and 48.0% on the LIBERO-PRO benchmark. Finally, experiments conducted in the real world using the Galaxea R1 Lite platform confirm its broad applicability across diverse tasks, especially long-horizon tasks. All datasets, checkpoints, and code will be released to the public domain following the acceptance of this work for future research.

Xiaoquan Sun, Zetian Xu, Chen Cao +9

INFIFORCE Intelligent Technology Co., Ltd. Hangzhou, China · Huazhong University of Science and Technology, Wuhan, China · The University of Hong Kong, Hong Kong SAR, China +1

Vision-Language-Action Models Robotic Manipulation Long-Horizon Robotic Manipulation Robustness of VLA Models

Mar 9, 2026

$Δ$ VLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation

Recent vision-language-action (VLA) models have significantly advanced robotic manipulation by unifying perception, reasoning, and control. To achieve such integration, recent studies adopt a predictive paradigm that models future visual states or world knowledge to guide action generation. However, these models emphasize forecasting outcomes rather than reasoning about the underlying process of change, which is essential for determining how to act. To address this, we propose

Δ

VLA, a prior-guided framework that models world-knowledge variations relative to an explicit current-world knowledge prior for action generation, rather than regressing absolute future world states. Specifically, 1) to construct the current world knowledge prior, we propose the Prior-Guided WorldKnowledge Extractor (PWKE). It extracts manipulable regions, spatial relations, and semantic cues from the visual input, guided by auxiliary heads and prior pseudo labels, thus reducing redundancy. 2) Building upon this, to represent how world knowledge evolves under actions, we introduce the Latent World Variation Quantization (LWVQ). It learns a discrete latent space via a VQ-VAE objective to encode world knowledge variations, shifting prediction from full modalities to compact latent. 3)Moreover, to mitigate interference during variation modeling, we design the Conditional Variation Attention (CV-Atten), whichpromotes disentangled learning and preserves the independence of knowledge representations. Extensive experiments on both simulated benchmarks and real-world robotic tasks demonstrate

Δ

VLA achieves state-of-the-art performance while improving efficiency. Code and real-world execution videos are available at https://github.com/JiuTian-VL/DeltaVLA.

Yijie Zhu, Jie He, Rui Shao +4

Harbin Institute of Technology, Shenzhen, Shenzhen 518055, China · Great Bay University, Dongguan 523000, China · Information Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China +1

Vision-Language-Action Models VLMs for Robotics World Models for Robotics Efficient VLA Models

Mar 9, 2026

SaiVLA-0: Cerebrum--Pons--Cerebellum Tripartite Architecture for Compute-Aware Vision-Language-Action

We revisit Vision-Language-Action through a neuroscience-inspired triad. Biologically, the Cerebrum provides stable high-level multimodal priors and remains frozen; the Pons Adapter integrates these cortical features with real-time proprioceptive inputs and compiles intent into execution-ready tokens; and the Cerebellum (ParaCAT) performs fast, parallel categorical decoding for online control, with hysteresis/EMA/temperature/entropy for stability. A fixed-ratio schedule and two-stage feature caching make the system compute-aware and reproducible. Inspired by active, foveated vision, our wrist ROIs are geometrically tied to the end-effector via calibrated projection, providing a movement-stabilized, high-resolution view that is sensitive to fine-grained pose changes and complements the global context of the main view. The design is modular: upgrading the Cerebrum only retrains the Pons; changing robots only trains the Cerebellum; cerebellum-only RL can further refine control without touching high-level semantics. As a concept-and-protocol paper with preliminary evidence, we outline a timing protocol under matched conditions (GPU, resolution, batch) to verify anticipated efficiency gains. We also report preliminary LIBERO evidence showing that split feature caching reduces training time (7.5h to 4.5h) and improves average success (86.5% to 92.5%) under official N1.5 head-only training, and that SaiVLA0 reaches 99.0% mean success.

Xiang Shi, Wenlong Huang, Menglin Zou +1

Vision-Language-Action Models Efficient VLA Models Robotic Perception

Mar 9, 2026

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA

While Vision-Language-Action (VLA) models have demonstrated remarkable success in robotic manipulation, their application has largely been confined to low-degree-of-freedom end-effectors performing simple, vision-guided pick-and-place tasks. Extending these models to human-like, bimanual dexterous manipulation-specifically contact-rich in-hand operations-introduces critical challenges in high-fidelity data acquisition, multi-skill learning, and multimodal sensory fusion. In this paper, we propose an integrated framework to address these bottlenecks, built upon two components. First, we introduce IMCopilot (In-hand Manipulation Copilot), a suite of reinforcement learning-trained atomic skills that plays a dual role: it acts as a shared-autonomy assistant to simplify teleoperation data collection, and it serves as a callable low-level execution primitive for the VLA. Second, we present MoDE-VLA (Mixture-of-Dexterous-Experts VLA), an architecture that seamlessly integrates heterogeneous force and tactile modalities into a pretrained VLA backbone. By utilizing a residual injection mechanism, MoDE-VLA enables contact-aware refinement without degrading the model's pretrained knowledge. We validate our approach on four tasks of escalating complexity, demonstrating doubled success rate improvement over the baseline in dexterous contact-rich tasks.

Tutian Tang, Xingyu Ji, Wanli Xing +7

Shanghai Jiao Tong University · Shanghai AI Lab · Sharpa +3

In-Hand Manipulation Contact-Rich Robotic Manipulation Vision-Language-Action Models Bimanual Robotic Manipulation VLMs for Robotics Tactile Sensing for Robotic Manipulation

Mar 9, 2026

SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving

Recent advances in Vision-Language-Action (VLA) models have shown promising capabilities in autonomous driving by leveraging the understanding and reasoning strengths of Large Language Models(LLMs).However, our empirical analysis reveals that directly applying existing token-level MoE mechanisms--which are inherited from LLM architectures--to VLA models results in unstable performance and safety degradation in autonomous driving, highlighting a misalignment between token-based expert specialization and scene-level decision-making.To address this, we propose SAMoE-VLA, a scene-adaptive Vision-Language-Action framework that conditions expert selection on structured scene representations instead of token embeddings. Our key idea is to derive the MoE routing signal from bird's-eye-view (BEV) features that encapsulates traffic scene context, enabling scenario-dependent expert weighting and merging tailored to distinct driving conditions. Furthermore, to support temporally consistent reasoning across world-knowledge, perception, language, and action, we introduce a Conditional Cross-Modal Causal Attention mechanism that integrates world state, linguistic intent, and action history into a unified causal reasoning process. Extensive experiments on the nuScenes open loop planning dataset and LangAuto closed-loop benchmark demonstrate that SAMoE-VLA achieves state-of-the-art performance, outperforming prior VLA-based and world-model-based approaches with fewer parameters.Our code will be released soon.

Zihan You, Hongwei Liu, Chenxu Dang +4

Institute for AI Industry Research (AIR), Tsinghua University · School of Instrument Science and Engineering, Southeast University · Zhili College, Tsinghua University +3

VLMs for Autonomous Driving Vision-Language-Action Models Autonomous Driving Planning Mixture of Experts Cross-Modal Attention

Mar 9, 2026

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

Vision-language-action (VLA) models achieve favorable task performance, yet runtime errors in closed-loop execution evolve with alternating updates of actions and observations. Existing VLA quantization methods mainly trade off inference speed and model performance while rarely investigating how quantization alters runtime errors. By comparing error distributions between full-precision and quantized models, we identify distinct evolutionary patterns for the two types of errors: quantization enlarges the variance of translation error distributions and increases their dispersion, whereas the distribution center of rotation errors gradually shifts across execution steps, demonstrating cumulative drift. Motivated by this observation, we rethink the optimal quantization strategy for VLA models and propose DyQ-VLA, a runtime-error-aware quantization framework, which dynamically selects activation precision according to execution steps and tracks as well as compensates rotation errors via accumulated quantization residuals. Corresponding operators and runtime adaptation strategies are devised within the framework to enable dynamic-precision execution. Experiments show that DyQ-VLA achieves a 1.88 to 1.93 inference speedups while maintaining comparable or higher average task success rates. Moreover, it reduces mean execution steps by 17.7% to 19.8%. Our code is here: https://anonymous.4open.science/r/DyQ-VLA-7F51/.

Zihao Zheng, Hangyu Cao, Chibang Tao +9

School of Computer Science, Peking University, Beijing, China. · School of Software Engineering, South China University of Technology, Guangzhou, China. · School of Artificial Intelligence, Beijing Normal University, Beijing, China. +1

VLM Quantization Efficient VLA Model Inference Efficient VLA Models Activation Quantization Vision-Language-Action Models Neural Network Quantization

Mar 8, 2026

TempoFit: Plug-and-Play Layer-Wise Temporal KV Memory for Long-Horizon Vision-Language-Action Manipulation

Pretrained Vision-Language-Action (VLA) policies have achieved strong single-step manipulation, but their inference remains largely memoryless, which is brittle in non-Markovian long-horizon settings with occlusion, state aliasing, and subtle post-action changes. Prior approaches inject history either by stacking frames, which scales visual tokens and latency while adding near-duplicate pixels, or by learning additional temporal interfaces that require (re-)training and may break the original single-frame inference graph. We present TempoFit, a training-free temporal retrofit that upgrades frozen VLAs through state-level memory. Our key insight is that prefix attention K/V already form a model-native, content-addressable runtime state; reusing them across timesteps introduces history without new tokens or trainable modules. TempoFit stores layer-wise FIFO prefix K/V at selected intermediate layers, performs parameter-free K-to-K retrieval with Frame-Gap Temporal Bias (FGTB), a fixed recency bias inspired by positional biases in NLP, to keep decisions present-dominant, and injects the retrieved context via pre-attention residual loading with norm-preserving rescaling to avoid distribution shift under frozen weights. On LIBERO-LONG, TempoFit improves strong pretrained backbones by up to +4.0% average success rate while maintaining near-real-time latency, and it transfers consistently to CALVIN and real-robot long-horizon tasks.

Jun Sun, Boyu Yang, Jiahao Zhang +7

Xi’an Jiaotong-Liverpool University

Memory-Augmented VLMs Vision-Language-Action Models Long-Horizon Robotic Manipulation

Mar 8, 2026

Adaptive Capacity Allocation for Vision Language Action Fine-tuning

Vision language action models (VLAs) are increasingly used for Physical AI, but deploying a pre-trained VLA model to unseen environments, embodiments, or tasks still requires adaptation. Parameter-efficient fine-tuning (PEFT), especially LoRA, is common for VLA policies, yet the exposed capacity knob, the rank, does not transfer uniformly: robotics transfer exhibits a higher and task-varying intrinsic rank than language fine-tuning. Small ranks suffice for LLMs (e.g.,

r \in \{4, 8\}

), while spectral analyses indicate VLAs may require much larger ranks (e.g.,

r \approx 128

) or near-full rank, a mismatch that worsens in multi-task settings. We present LoRA-SP (Select-Prune), a rank-adaptive fine-tuning method that replaces fixed-rank updates with input- and layer-wise capacity. LoRA-SP uses an SVD-style parameterization with a small router whose nonnegative scores act as singular values over a shared vector bank. The active set is chosen by an energy target on the cumulative squared scores

E(k) \ge η

, providing a direct link to approximation error via our spectral analysis. During training,

η

concentrates energy on a few directions and teaches the router to rely on fewer vectors while preserving accuracy. This yields compact adapters that reduce cross-task interference and improve generalization. On four real-robot manipulation tasks collected on an unseen AgileX PiPER arm, across two VLA backbones (

π_0

and SmolVLA), LoRA-SP matches or exceeds full fine-tuning with far fewer trainable parameters, and improves multi-task success by up to 31.6% over standard LoRA while remaining robust to rank choice.

Donghoon Kim, Minji Bae, Unghui Nam +4

Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea

Parameter-Efficient Fine-Tuning Low-Rank Adaptation Vision-Language-Action Models Robotics

Mar 6, 2026

History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation

Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have demonstrated strong navigation performance, but their high computational cost introduces latency that limits real-time deployment. We propose a training-free spatio-temporal vision token pruning framework tailored to VLA-based VLN. We apply spatial token selection to the current view, alongside spatio-temporal compression for historical memories, enabling efficient long-horizon inference while reducing redundant computation. Leveraging attention-based token importance and query-guided spatio-temporal filtering, the proposed approach preserves navigation-relevant information without retraining or modifying pretrained models, allowing plug-and-play integration into existing VLA systems. Through experiments on standard VLN benchmarks, we confirm that our method significantly outperforms existing pruning strategies. It successfully preserves superior navigation accuracy under extreme pruning scenarios, all while maintaining the highly competitive inference efficiency. Real-world deployment on a Unitree Go2 quadruped robot further validates reliable and low-latency instruction-following navigation under practical robotic constraints. We hope this work helps bridge the gap between large-scale multimodal modeling and efficient, real-time embodied deployment in robotic navigation systems. Project Page: https://wqtwjt1996.github.io/publications/2026-vln.html

Qitong Wang, Yijun Liang, Ming Li +2

The authors are with the Department of Computer and Information Sciences at the University of Delaware, Newark, DE 19711, USA. · The authors are with the University of Maryland’s Department of Computer Science, College Park, MD 20742, USA. · The author is with the Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi 7909, UAE.

Efficient VLM Inference Token Pruning Vision-Language Navigation Vision-Language-Action Models Visual Token Pruning

Mar 6, 2026

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration

Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies. However, their reliability under Out-of-Distribution (OOD) instructions remains underexplored. In this paper, we reveal a critical failure mode in which VLA policies continue executing visually plausible actions even when the language instruction contradicts the scene. We refer to this phenomenon as linguistic blindness, where VLA policies prioritize visual priors over instruction semantics during action generation. To systematically analyze this issue, we introduce ICBench, a diagnostic benchmark constructed from the LIBERO dataset that probes language-action coupling by injecting controlled OOD instruction contradictions while keeping the visual environment unchanged. Evaluations on three representative VLA architectures, including Pi0, Pi0.5 and OpenVLA OFT, show that these models frequently succeed at tasks despite logically impossible instructions, revealing a strong visual bias in action generation. To mitigate this issue, we propose Instruction-Guided Attention Recalibration (IGAR), a train-free inference-time mechanism that rebalances attention distributions to restore the influence of language instructions. IGAR operates without retraining or architectural modification and can be directly applied to existing VLA models. Experiments across 30 LIBERO tasks demonstrate that IGAR substantially reduces erroneous execution under OOD contradictory instructions while preserving baseline task performance. We additionally validate the approach on a real Franka robotic arm, where IGAR effectively prevents manipulation triggered by inconsistent instructions.

Ninghao Zhang, Bin Zhu, Shijie Zhou +1

Tsinghua University · Singapore Management University · Institute of Trustworthy Embodied AI, Fudan University +1

Vision-Language-Action Models Robustness of VLA Models