Vision-Language-Action Models

Also known as VLA

Ask about this topic

Overview

These models combine vision-language backbones with action generators that produce continuous motion or discrete action tokens, often in chunks and with proprioceptive input. They are commonly trained on robot demonstrations, with flow-matching and diffusion policies, reinforcement fine-tuning, and predictive world models used to improve control and planning. Research spans tabletop and bimanual manipulation, mobile and aerial navigation, autonomous driving, and humanoid control, evaluated on benchmarks such as LIBERO, CALVIN, RoboTwin, and driving simulators. A central challenge is making broad visual and language competence translate into reliable closed-loop behavior under new objects, viewpoints, embodiments, delays, and safety constraints; benchmark success can still conceal weak instruction grounding and sim-to-real failures.

Latest papers

CardsList

1,154 papers249 papers in the last four weeks, up 144% on the four weeks before. 1.5% of all new papers.

Aug 25, 2026

TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks

Robot actions are inherently embodiment-specific and only weakly aligned with image-space visual changes, limiting their effectiveness as conditioning signals for robot world models. In contrast, visual tracks provide an embodiment-agnostic representation of how task-relevant points move through a scene, offering dense image-space guidance for accurate and spatially precise future video prediction. Building on this observation, we propose TrAct, a world-model-based robot decision-making framework that uses visual tracks as an intermediate interface between control and prediction. TrAct consists of three components: a Vision-Language-Action-and-Track model (VLAT) that jointly predicts candidate actions and corresponding visual tracks from the current observation and language instruction; a track-conditioned world model (TWM) that predicts future visual outcomes conditioned on the proposed tracks; and a vision-language reward model (VLAC) that scores the predicted outcomes. At inference time, VLAT generates candidate action-track pairs, TWM rolls out their visual consequences, and VLAC selects the track whose predicted outcome best satisfies the instruction; the action paired with the selected track is then executed by the robot. Experiments on the proposed LIBERO-INTEGRAL benchmark and real-world Franka manipulation show that TrAct improves success rates from 27% to 55% in simulation and from 49% to 76% on real-world tasks compared with the strong VLA baseline π0.5π_{0.5}. Furthermore, TWM consistently improves video prediction quality over the action-conditioned world model (AWM). These results demonstrate that visual tracks provide an effective shared interface between robot control and visual prediction, enabling more accurate world modeling and stronger robot generalization.

Zhi Cao, Howard Ji, Kevin Zhang +4

University of Michigan · Stanford University

Vision-Based Robot ControlWorld Models for RoboticsWorld Model LearningVision-Language-Action Models
AskPDF
Aug 25, 2026

Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models

While Vision-Language-Action (VLA) models pretrained on large-scale robot datasets provide a strong foundation for robot manipulation, their performance can degrade when adapted to new tasks with limited task-specific demonstrations. Retrieval offers a practical way to reuse existing demonstrations for data-efficient adaptation, but existing methods often rely on visual similarity, state-action representations, or task-level language matching. These approaches may overlook the hierarchical structure of long-horizon manipulation tasks, where complete task matches are rare but reusable skills are often abundant. To address this challenge, we propose Hierarchical Skill Retrieval (HSR), a retrieval framework for data-efficient VLA adaptation. Specifically, HSR first decomposes a target task into candidate skill sequences. It evaluates each plan based on both semantic plausibility and skill reliability estimated from the prior dataset. The selected decomposition is then used for hybrid retrieval. This combines subtask-level language retrieval with behavior-feature reranking to identify demonstrations that are both semantically relevant and compatible with the target task. Finally, we adapt the policy through a two-stage pretraining and finetuning pipeline, which separates general skill acquisition from task-specific adaptation. Experiments on the LIBERO benchmark and several real-world robot manipulation tasks show that HSR improves the average success rate by 10.3% and 21.3% over the strongest baseline, respectively. These results demonstrate the effectiveness of structured skill-level retrieval for data-efficient VLA adaptation. Videos and code are available at https://hoar012.github.io/HSR-Project.

Haoran Hao, Shahram Najam Syed, Jeff Schneider +1

Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213.

Data-Efficient Robot LearningVision-Language-Action ModelsRobot Skill LearningLong-Horizon Robotic Manipulation
AskPDF
Aug 24, 2026

Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the local objective served by the behavior under the instruction. Future-based supervision enriches action learning with frames, latent observations, trajectories, or motion representations, but these signals capture particular realizations of what may happen rather than the shared semantic objective of the forthcoming behavior. We propose Intention Distillation (INDI), which distills behavior-level intent into the action decoder. During training, a frozen teacher VLM interprets a demonstrated segment from the current observation, instruction, coarse action summary, and corresponding execution video. From its standard inputs, the deployed VLA recovers the resulting multimodal intent representation at an intermediate decoder layer and uses it to organize action prediction together with representations of how the behavior unfolds and what it achieves. On SimplerEnv-Bridge, INDI improves GR00T-N1.7 from 64.3% to 84.7%, and on RoboCasa Kitchen it improves the controlled GR00T-N1.7 baseline from 64.1% to 70.3%, with consistent gains on π0.5π_{0.5} across both benchmarks. In real-world tasks, INDI improves average success from 62.0% to 68.7%, with gains of up to 12.0 pp on longer-horizon tasks. Further analyses show that the recovered latent is used by the decoder, captures behavior objective and execution progress, and organizes downstream predictions in an objective-dependent manner. These results show that action decoders benefit from explicitly modeling the semantic objective of the behavior they generate.

Sangoh Lee, Sangwoo Mo, Wook-Shin Han

GSAI, POSTECH · IME, POSTECH

Vision-Language-Action ModelsRobotic ManipulationReasoning for VLA Models
AskPDF
Aug 24, 2026

ROS2SmolVLA: Enabling Small Vision-Language-Action Models for Integration into Industrial-Grade Lightweight Robots

Industrial demand changes the paradigms of production. Due to smaller batch sizes and more variations in products, companies face a growing challenge to adopt more adaptive production systems. In particular, robot-based automation is usually static and fails to respond to constantly changing processes. Vision-Language-Action (VLA) Models are a promising opportunity to mitigate this challenge by generating robot actions based on the observed system state. However, current research either focuses on large models that cannot be computed on premise, creating compliance and security challenges, or use lab-grade robot hardware that obscures exploitation in real industrial settings. In this work, we adapt Hugging Face's SmolVLA for Universal Robots lightweight robots. Further, we release the open-source repository ROS2SmolVLA that implements an interface for ROS 2 to SmolVLA, and makes it applicable for industrial-grade hardware. By this, we allow a lenient adoption into lab and industrial environments. We validate the functionality of SmolVLA for a Universal Robots UR10e using a pick-and-place task and give implementation guidelines. Our findings support that SmolVLA is a well-suited option for small-sized tasks that need to be computed on premise.

Nils Mandischer, Noah Böckmann, Ludwig Holl +1

University of Augsburg, Chair of Mechatronics, Am Technologiezentrum 8, 86159 Augsburg, Germany

RoboticsIndustrial RoboticsVision-Based Robot ControlVision-Language-Action Models
AskPDF
Aug 24, 2026

Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation

Retrieval can efficiently and effectively augment a frozen vision--language--action (VLA) policy without retraining, yet retrieved text becomes a control intervention once it enters the executed prompt. In a matched audit, raw appended text reduces mean success from 92.47% to 3.00%, while meaningful and length-matched meaningless appends both fail on all 500 states. This result identifies prompt-form collapse: changing the instruction form, rather than adding useful semantics, can dominate execution. We introduce TOWN-VLA (Think Only When Needed), a prompt-authority interface that separates candidate generation from permission to alter the policy input. A fixed compatibility rule authorizes a canonical compact instruction; otherwise, the interface restores the original Base prompt exactly. Across 900 audited routes, every route follows this contract: 525 routes recover Base with matching hashes, and all 375 authorized prompts preserve the task signature. On a matched 4×74\times7 LIBERO-Plus evaluation with 10{,}030 episodes per method, success rises from 69.5% to 73.1% (+362+362 episodes; 95% CI 1.89--5.45 points), improving on six perturbation axes and all four suites. On a physical PiPER arm with a frozen \pizerofive{} checkpoint, success rises from 52.7% to 78.7% over 150 trials per method (p=3.16×10−6p=3.16\times10^{-6}). Prompt authority is enforceable for a frozen controller; oracle-free admission calibration is the next deployment target.

Zhiruo Zhou, Zelin Li, Xiwen Chen +4

SIGS, Tsinghua University, China · Wuhan University of Technology, China · Shanghai Jiao Tong University, China +3

Vision-Language-Action ModelsVLMs for RoboticsRobustness of VLA Models
AskPDF
Aug 24, 2026

Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation

Vision-language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or opaque action tokens, creating brittle interfaces between multimodal reasoning and robot execution. We present Pointing-VLA, a typed hidden-state spatial readout built on Embodied-R1. Geometry-specific heads predict normalized points, object-functional grounding (OFG) heatmaps, and visual trajectories without serializing geometry as text. For the evaluated Bridge/WidowX and physical pick-place deployments, an explicit execution contract assigns PICK to source-conditioned OFG and PLACE to Pointing, providing direct stage-aligned spatial targets. Pointing-VLA achieves SOTA performance on Bridge/WidowX, averaging 72.9% across the evaluated four-task set without Bridge-specific finetuning under collision-enabled CuRobo execution. Pointing and OFG show complementary strengths across native and cross-dataset evaluations. The OFG/contact readout transfers to NORA-1.5, preserving or improving success while reducing recorded controller time by more than 20×\times; typed heads are also 6.68--6.90×\times faster than Embodied-R1 text decoding on a shared external suite. When integrated as spatial guidance for a π0.5π_{0.5} action policy, Pointing-VLA raises autonomous real-robot success from 52.7% to 80.7% across three visual contexts. These results establish typed spatial readouts as an efficient, inspectable interface between embodied reasoning and robot execution.

Xiwen Chen, Zelin Li, Zhiruo Zhou +3

SIGS, Tsinghua University, China · Shanghai Jiao Tong University, China · Wuhan University of Technology, China +2

Vision-Language-Action ModelsRobotic ManipulationEfficient VLA Model Inference
AskPDF
Aug 24, 2026

InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation

Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions. A key test of such generality is whether policies actually follow language instructions. Yet many manipulation benchmarks leave this ability underdetermined: the intended object or destination is often visually salient or uniquely feasible, allowing policies to succeed without grounding the instruction. We argue that instruction-following evaluation should be text-indispensable: multiple actions should be visually and physically plausible, while only one should be consistent with the language instruction. We introduce InstructMove, a text-indispensable benchmark for instruction-following manipulation. InstructMove instantiates this principle in pick-and-place scenes with semantic distractors, decomposing instruction following into category identification, attribute discrimination, spatial reasoning, and compositional pick-and-place. InstructMove supports a train-eval protocol with InstructMove training data and held-out evaluation tasks, with additional diagnostics for language dependence. Experiments with representative VLA policies show that InstructMove provides a controlled testbed for diagnosing visual shortcuts and that InstructMove simulation data can improve real-world instruction-following manipulation performance. Code: https://github.com/HorizonRobotics/RoboOrchardSim

Mengao Zhao, Ziang Li, Chaodong Huang +15

Horizon Robotics · Southeast University · Huazhong University of Science and Technology +1

Robot Manipulation BenchmarksLanguage-Conditioned Robot ManipulationRobotic ManipulationVision-Language-Action Models
AskPDF
Aug 24, 2026

UniMem: Unifying Multimodal Memory and Control for Vision-Language-Action Models

While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning to achieve strong performance on long-horizon tasks, they often struggle with non-Markovian tasks that require memory. Existing approaches to memory typically involve additional Vision-Language-Models (VLMs) for long-term memory management, introducing a memory bottleneck and a fractured training pipeline. Conditioning on multiple historical frames can provide the VLA with access to more descriptive features of past scenes, but can degrade performance if frames are chosen at arbitrary, fixed intervals. To address these limitations, we present UniMem, a framework that unifies high-level, multimodal memory and low-level control under one backbone. UniMem employs an event classifier for memory updates, a keyframe encoder for dense spatial memory, and a keyframe caching technique to minimize overhead during policy rollouts. We evaluate UniMem across five simulation and four hardware tasks targeting sequential and spatial memory, demonstrating that our unified, single-model system outperforms fixed-interval image sampling baselines (93.4% vs. 68.2%) in simulation and hierarchical baselines (80.0% vs. 43.5%) in hardware, while offering faster inference and a simple training pipeline for easy adoption. Project website: https://losterberg3.github.io/unimem-vla/

Lars Osterberg, Maggie Wang, Mac Schwager

Stanford University, Stanford, CA, USA

Memory-Augmented VLMsVision-Language-Action ModelsVLMs for RoboticsEfficient VLA Models
AskPDF
Aug 23, 2026

WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning

Vision-language-action policies inherit both capabilities and input representations from pretrained vision-language models, showing great potential for robotic manipulation across diverse industrial settings. As these policies increasingly use interaction history, organizing the representation of historical observations determines how experiences enter temporal context and how relationships across time are modeled, which is a generally ignored challenge in previous works. In this work, we believe solving this challenge requires an architectural reconstruction and propose WorldToken. WorldToken encodes each timestep's observations into one world token, processes the resulting history with a causal Transformer, and generates action chunks with a diffusion action head. Unified token enables long horizon tasks while relieving the memory requirement of the temporal backbone, hence improving performance. This design also offers high interpretability and allows advances in language modeling, such as pre-training and scaling, to be transferred to robot interaction policies. In RoboCasa experiments, WorldToken successfully handles most tasks with 85M parameters and achieves 59.4% mean closed-loop success close to π0.5π_{0.5} with 3.35B parameters. On the memory benchmark RMBench Blocks Ranking, WorldToken can reach the context of two minutes and achieves a success rate of 95%. In addition, holdout action RMSE is well described by power-law fits, and its closed-loop success rate improves consistently with increasing training data size in a study involving approximately 350,000 closed-loop evaluation episodes across 50 trained policies on RoboCasa, showing its scaling potential. We also conduct experiments to analyze information preservation and history use in WorldToken, providing empirical grounding for future work.

Chunkai Yang, Andong Yang, Di Huang +2

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China. · Department of Electronic Engineering, Tsinghua University, Beijing, China. · Institute for AI Industry Research, Tsinghua University, Beijing, China.

Robot Policy LearningLong-Horizon Robotic ManipulationRobot Skill LearningVision-Language-Action ModelsRobot Imitation LearningRobot Learning
AskPDF
Aug 23, 2026

Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking

Query-based Vision-Language-Action (VLA) models offer low-latency inference that is attractive for bimanual robotic manipulation, but we observe that they can still exhibit discontinuous actions and execution failures in complex dual-arm tasks. We hypothesize that unstable multi-view and language fusion is one contributing factor in these failures, often coinciding with attention spreading to distracting regions. To improve robustness, we introduce the Modality Masking Mechanism (M3), an embarrassingly simple, training-only strategy that requires no architectural changes or large-scale robot pretraining. M3 stochastically masks subsets of modality channels during training, exposing the policy to controlled partial observations and encouraging it to rely less on distracting cues and more on evidence that remains reliable. We evaluate M3 on ten bimanual tasks from RoboTwin 2.0 and on three long-horizon real-world tasks. Compared with the Adapter baseline, M3 improves average success by 21.7% in the Clean setting and 11.4% in Clean2Rand, where policies are trained on clean demonstrations and evaluated on randomized scenes, while also improving averaged real-world full-task success by over 30%. These results suggest that structured training-time masking is a practical way to improve the robustness of query-based VLA policies for bimanual manipulation.

Dongzhou Cheng, Ziang Li, Yixiao Zhou +6

Southeast University · Shanghai Innovation Institute · Wuhan University +4

Vision-Language-Action ModelsRobustness of VLA ModelsBimanual Robotic Manipulation
AskPDF
Aug 21, 2026

Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in vision-language models and recently explored for embodied agents. In embodied agents, tokens not only support perception and semantic understanding but also directly affect latency-sensitive closed-loop robot action prediction. Existing schemes typically guide compression using redundancy or importance cues, such as visual similarity, attention scores, and saliency. However, these cues only indirectly measure the key factor for safe compression: how much a token can change before causing an unacceptable deviation in downstream actions. This receiver-dependent tolerance is closely related to the principle of just noticeable difference (JND). Classical JND characterizes signal tolerance in the human visual system, while machine-oriented JND extends this concept to downstream machine responses. Building on this progression, we introduce Action-JND, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control. A token change is considered admissible only when the induced action deviation remains within a tolerated margin. To realize this concept, we develop a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum tolerable perturbation while preserving policy responses. The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms, including stale-KV reuse and token pruning, prioritizing action-tolerant tokens for compression. Experiments on the LIBERO benchmark with OpenVLA and OpenVLA-OFT demonstrate that Action-JND consistently improves compression reliability, especially under aggressive compression ratios.

Zhuoyuan Li, Rui Zhao, Jin Wang +5

Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong · School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798 · Bytedance Inc. +2

Vision-Language-Action ModelsVisual Token PruningVisual Token Compression
AskPDF
Aug 21, 2026

ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation

Manipulating moving objects requires a policy to anticipate contact events, yet vision-language-action (VLA) policies are commonly fine-tuned from the current observation alone. World action models (WAMs) learn predictive dynamics, but running a video-scale teacher or explicitly imagining future frames at deployment is costly. We introduce ForeTime-VLA, a dense pi0.5 policy that distills a future-aware, action-equivalent representation from a frozen Fast-WAM-derived teacher while remaining causal at inference. Offline, current and future video latents are compressed into a whitened 64-D target. Online, an eight-frame history encoder predicts this target together with manipulation phase and normalized time-to-transition. Four future tokens and one phase token condition the VLM prefix, while the predicted future and transition horizon condition the action expert. Training retains the original flow-matching action target and adds cosine, relational geometry, phase, time-to-transition, and action-equivalence objectives. On a deduplicated conveyor-belt dataset, we compare 40k-step checkpoints on 768 matched windows per split. Test MAE decreases from 0.134119 to 0.130593 (2.63%; paired-bootstrap 95% CI: 0.82-4.48% improvement), and test L2 decreases by 3.02%, at a 2.46-2.93% latency cost. In quantitative real-robot evaluation, ForeTime-VLA achieves 81.1% stationary and 58.9% slow-moving grasp success, exceeding the next-best reference by 12.2 and 22.2 percentage points, respectively. Across three belt speeds, it completes 44/90 grasps versus 23/90 for pi0.5, including 11/30 versus 2/30 at fast speed. The agreement between offline orientation gains and reduced real-robot contact-pose failures supports causal future-token distillation as an effective way to improve dynamic manipulation without deploying the world-model teacher.

Siyuan Ma, Yutian Zhang, Boshi Zhang +4

Tsinghua University, Beijing, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · Harbin Institute of Technology, Harbin, China +1

Visuomotor Policy LearningVision-Language-Action ModelsKnowledge Distillation
AskPDF
Aug 20, 2026

Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model

Vision-language-action (VLA) models can follow natural-language (NL) task instructions, but such instructions may not precisely specify safety-critical or spatiotemporal requirements on the resulting behavior. We introduce Logic-VLA, a formal-requirement-aware VLA that conditions on Signal Temporal Logic (STL) specifications supplied at inference time. Logic-VLA uses a syntax-graph-based STL encoder pre-trained to capture temporal logic semantics. Policy adaptation proceeds in two stages: STL-conditioned supervised fine-tuning on satisfying demonstrations is followed by trajectory-level preference optimization over matched satisfying-violating rollout pairs using a flow-matching surrogate for Identity Preference Optimization. This formulation improves formal requirement satisfaction while preserving the nominal NL task. We evaluate Logic-VLA in closed-loop quadcopter navigation simulation across randomized photorealistic environments and test generalization to STL formulas unseen during training. Across the evaluation benchmarks, Logic-VLA improves STL satisfaction rate over an STL-blind base policy by 24.8 to 40.7 percentage points (pp) while reducing nominal NL task success by at most 1.8 pp, showing that a single VLA can adapt its behavior to varying formal requirements without requiring a separate policy for each specification.

Celina Shiyu Wang, Yiqi Zhao, Junjie Ye +2

Thomas Lord Department of Computer Science, University of Southern California

Vision-Language-Action ModelsReasoning for VLA ModelsAerial VLN
AskPDF
Aug 20, 2026

EndoLIFT: Language-Disambiguated Latent-Conditioned Rectified Flow for Bidirectional Endoscopic Control

Routine gastrointestinal endoscopy is intrinsically bidirectional: the instrument is advanced to reach target anatomy and later withdrawn or retroflexed for inspection, while an external cue may require earlier reversal. When the requested phase changes before the visual scene does, nearly identical observations can require opposite axial actions. We identify and formalize this ambiguity in bidirectional endoscopic control as intent aliasing. We propose EndoLIFT (Endoscopic Language-Instruction Flow with Trajectory Latents), a vision-language-action policy that combines explicit language-based intent conditioning with a latent-conditioned rectified-flow action expert. The policy receives RGB, a language instruction, and the previous-action state; a 32-D variational trajectory latent stochastically conditions continuous action-chunk generation. Controlled same-observation instruction swaps establish that language selects the axial mode, independently of whether the trajectory latent is present. Relative to the matched model without latent conditioning, EndoLIFT improves navigation-direction accuracy by 11.1 percentage points and reduces wrong-direction advance by 83%. An architecture-controlled 1-bit mode-flag reference exhibits weaker canonical-anchor switching, while EndoLIFT retains 82.8% intent-following accuracy across 44 held-out linguistic variants. In closed-loop evaluation, EndoLIFT improves overall success by 30 percentage points over EndoLIFT w/o VTL on both the seen colon phantom and the unseen lung and stomach phantoms, and completes 10/10 ex-vivo porcine-trachea trials. These results separate language-based intent selection from the trajectory latent's contribution to directional correctness and robust retraction.

Chi Kit Ng, Yidong Zhang, Lui Siu Hing +9

The Chinese University of Hong Kong, Hong Kong SAR, China · The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China

Robotic ControlVision-Language-Action ModelsLanguage-Conditioned Robot Control
AskPDF
Aug 20, 2026

EXIMO: VLM Guided Exploration of VLA Policies

How to efficiently finetune robot policies to learn new tasks on the fly? State of the art robotic manipulation policies are based on behaviour cloning of large vision-language-action (VLA) models with billions of parameters on huge teleoperation datasets. While this simple approach has enabled significant advances for robotic manipulation, finetuning of VLA policies for learning new tasks still remains an open problem. In particular, collecting teleoperation datasets requires hundreds of hours of expensive human labour and the alternative, reinforcement learning (RL), can be notoriously sample-inefficient especially for long-horizon tasks. In addition, RL with VLAs imposes several challenges due to the model's size and architectural design. In this work, we propose EXIMO, an efficient algorithm for finetuning of VLA policies. EXIMO operates in three stages: explore, imitate, and optimize. During the explore phase, EXIMO equips the VLA with a vision language model (VLM) that acts as a planner. The VLM thinks and breaks down challenging long-horizon problems into shorter ones for the VLA. The VLM, together with the VLA, is used to collect an orchestrated dataset on new tasks. During the imitate phase, the VLA is finetuned with the orchestrated data. Finally, during the optimize stage, we use residual off-policy RL to further finetune the policy. In our experiments, we ablate all three stages of EXIMO and show that it outperforms existing approaches significantly in terms of sample-efficiency and final performance.

Bhavya Sukhija, Oliver Groth, Mohit Shridhar +5

Google DeepMind

Data-Efficient Robot LearningVision-Language-Action ModelsLong-Horizon Robotic ManipulationVLMs for Robotics
AskPDF
Aug 19, 2026

Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation

State-of-the-art vision-language-action (VLA) models such as π0.5π_{0.5} exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops. Finetuning the VLA on in-domain expert data from the new embodiment improves performance on the expert task but leads to a loss in its original instruction following and behavioral priors. In this paper, we propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning. Our experiments show this finetuning scheme yields strong multi-task policies that, on the target robot, (1) inherit prior tasks distilled from the zero-shot model, (2) enable generalist instruction following, while (3) learning new skills from expert data with improved sample efficiency. We demonstrate the success of our approach across test sets probing generalization on a real ALOHA robot and a new simulation benchmark in RoboTwin. Video results are available at https://self-supervised-control.pages.dev/

Prachi Garg, Steve Xing, Prahit Yaugand +2

University of Illinois Urbana-Champaign

Robot LearningVision-Language-Action ModelsMulti-Task Robotic ManipulationInstruction Generalization in VLA Models
AskPDF
Aug 19, 2026

Role-Conditioned Sub-Token Routing for Efficient Vision-Language-Action Policies

Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficiency methods mainly reduce visual tokens, but aggressive token pruning becomes fragile because removing a token discards its entire representation. Sub-token compression provides a complementary alternative by retaining more tokens while reducing their value width. However, directly applying sub-token compression to VLA policies is less effective because information important for perception, language understanding, and control is distributed differently across the multimodal representation. We introduce Role-Conditioned Sub-Token Routing (RoleSub), which learns how to compress the value representations of retained tokens. After visual token reduction, RoleSub partitions each retained value representation into groups in an orthogonal space and uses a lightweight router to determine which groups should be preserved. The routing decision is conditioned on the token representation, a learned latent role representation, and language context. The same mechanism can also be applied to language values, allowing visual and language representations to be compressed without removing additional tokens. We evaluate RoleSub on OpenVLA-OFT-7B across the four LIBERO suites. At matched visual-KV budgets, RoleSub outperforms a trained token-only control in 33 of 36 settings, with the largest gains under aggressive compression. Combining visual and language compression reduces total KV to 9.2--11.3% of the original while retaining strong control performance on most tasks. These results show that reducing the representation within retained tokens provides an effective complement to token pruning for aggressive VLA compression.

Wei Jiang, Wei Wang

Futurewei Technologies San Jose, CA 95131, USA

Efficient VLA ModelsMultimodal Token CompressionVision-Language-Action ModelsKV-Cache Compression
AskPDF
Aug 18, 2026

LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action Models

Visual cues are increasingly adopted to guide robot learning, but whether Vision-Language-Action (VLA) models can reliably follow authorized cues while disregarding unauthorized ones remains unclear. Existing work covers only a narrow range of cue forms and focuses on final task success, providing only a coarse assessment of cue-following capability. Treating all visual cues as authorized also leaves safety risks of unauthorized following unexplored. To address these gaps, we introduce LIBERO-VIFO, a benchmark to evaluate both the capability and safety of visual cue following in VLA models. LIBERO-VIFO defines eight visual cue families spanning diverse forms. A total of four protocols in two parts are defined: Part I tests cue understanding and authorized following, while Part II evaluates unauthorized visual cue following under language-cue conflict and empty language conditions. Evaluating seven VLA models reveals that although visual cue understanding does not reliably translate into execution, current VLAs are able to execute cue-indicated tasks without language instruction, exposing an emerging risk of unauthorized visual cue following. Extended experiments on scene-instantiated cues, safety-critical settings, and real-robot deployment corroborate these findings. LIBERO-VIFO brings both the capability and safety of visual cue following into systematic evaluation, establishing visual-centric safety as a new perspective for the VLA community.

Zhengyan Qian, Rui Yan, Alex Jinpeng Wang +1

Vision-Language-Action ModelsSafety Evaluation of VLA Models
AskPDF
Aug 18, 2026

Geo-VLA: Geometry-Aware Vision-Language-Action Planning via Internalization of Map Semantics

Vision-language-action (VLA) models have advanced end-to-end autonomous driving by leveraging foundation models for semantic reasoning and long-tail generalization. However, their planning performance remains limited in complex driving environments because image-only representations inadequately capture planning-relevant road geometry and topology. In this paper, we propose Geo-VLA, a plug-and-play framework that enhances VLA models by learning geometry-aware visual representations. During training, Geo-VLA internalizes geometric map semantics to strengthen road-structure representations, while requiring no HD maps or additional lane information during inference. To support this approach, we introduce Geo-QA, a geometry-focused question-answering dataset that injects road geometry into vision-language representations through contrastive learning and instruction tuning. Experiments on NAVSIM v1 demonstrate that Geo-VLA consistently improves VLA planners with distinct action-generation architectures, achieving 92.1 PDMS and establishing a new state-of-the-art among single-camera VLA planners.

Ran Chen, Jiaxing Ren, Zhikun Zhang +3

University of Science and Technology Beijing Beijing, China

Vision-Language-Action ModelsAutonomous Driving Planning
AskPDF
Aug 18, 2026

Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal Policies

Frozen vision-language-action (VLA) policies are increasingly improved at test time by sampling additional policy behaviors or introducing external demonstrations. Yet there is little guidance for deciding which intervention a deployed policy actually needs. Additional sampling is useful only when better behavior already exists within the policy's stochastic rollouts and can be identified, whereas retrieval is most useful when the relevant action prior is not reliably represented by the policy. We study this decision through two measurable factors, recoverable headroom and retrieval complementarity, which characterize how much useful behavior is already available to recover and whether an external action prior fills a measurable gap. We evaluate an episode-level retry selector under retryable or parallel execution, together with retrieval across multiple frozen VLA policies and environments. The selector consistently recovers substantial latent capability across all tested VLA backbones on LIBERO, with gains of up to 21.0 success-rate points that closely track recoverable headroom. It also transfers to a different robot and simulator and remains effective under degraded observations, while experiments with autoregressive OpenVLA illustrate the distinction between available headroom and the ability to rank candidate rollouts. Retrieval behaves differently, improving the policy with the largest measured action-prior gap and providing further gains when combined with selection. Together, these results provide an empirical basis for characterizing test-time augmentation opportunities by separating capability that can be recovered from the frozen policy from behavioral priors that may need to be introduced externally.

Yuhwan Jeong, Kuk-Jin Yoon

KAIST, Visual Intelligence Lab.

Test-Time Adaptation of VLA ModelsRobot Policy LearningVision-Language-Action Models
AskPDF
Aug 18, 2026

EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Control

Long-horizon humanoid vision--language--action (VLA) control with head-mounted stereo cameras requires visual interfaces that can exploit complementary views while maintaining compatibility with pretrained representations. Existing interfaces often discard complementary stereo evidence or fuse additional observations without preserving the native primary-view pathway and adapting auxiliary information to robot embodiment. We present EATR-Stereo, an embodiment-aware token-routing framework that retains primary-view tokens and constructs primary-aligned Cross-View Auxiliary Tokens (CVATs) by querying the synchronized auxiliary-view token sequence. A body-segmented proprioceptive encoder further conditions token-wise auxiliary usage on robot configuration history, enabling selective incorporation of stereo evidence during action generation. The routed auxiliary stream augments the language and primary-visual context of a pretrained VLA while keeping its vision--language model frozen. On a 33-DoF physical humanoid with a 37-D proprioceptive state, we evaluate nine configurations in over-100-s search--approach--grasp--place--return tasks. EATR-Stereo achieves 60.0% full-task success, 100.0% grasp success, and 80.0% stage success. Under severe asymmetric occlusion, it improves recovery to 80% compared with 30% for CVAT alone. Ablation studies further show the importance of preserving primary tokens and combining cross-view auxiliary features with structured proprioceptive routing. These results demonstrate that selectively routed paired stereo evidence improves spatial grounding for reliable long-horizon humanoid VLA control.

Songwei Wu, Rui Zhao, Fan Yang +7

Harbin Institute of Technology · Honor

Robotic ControlVision-Language-Action ModelsVLMs for RoboticsLong-Horizon Robotic ManipulationStereo Vision
AskPDF
Aug 17, 2026

Inference-Time Attention Steering for Vision-Language-Action Driving Models

Vision-language-action (VLA) driving models couple a reasoning stage with a diffusion-based trajectory decoder, but do not give a direct way to redirect attention toward safety-critical actors at inference time without retraining. We studied a bounded additive pre-softmax attention bias on the visual tokens of detector localized traffic actors on Alpamayo-R1's Qwen3-VL backbone. It is applied as a fail open forward pre-hook with no weight changes. On 50 lane-change scenarios from the Physical AI World Model Synthetic dataset. The trajectory decoder shows a monotonic dose response in the bias magnitude, separate from a paired zero bias control at every tested magnitude. It reaches ≈17\approx 17,cm mean displacement with lateral shifts up to ∼140\sim 140\ cm at the clamp. A layer ablation places the action-relevant signal in late layers, where the effect increases with the number of hooked layers (2.0cm for the first 8 layers; 67.6cm for all 36). A per call injection audit explains why the Chain-of-Causation text never changes. The mask based bias never reaches the reasoning pathway in this serving stack, so the invariance is verified exposure, not robustness. Steered trajectories tend to shift toward the attended actor, suggesting the bias governs where the model looks rather than encoding a target behavior.

Darshan Nagendra Prasad, Lars Ullrich, Knut Graichen

FAU Erlangen-Nürnberg, Germany

Vision-Language-Action ModelsVLMs for Autonomous Driving
AskPDF
Aug 17, 2026

τ0τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce τ0τ_0-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

Xiaowei Cai, Yunuo Cai, Bingao Chen +36

Agibot Finch · Shanghai Innovation Institute · The Chinese University of Hong Kong

Robot Policy LearningLong-Horizon Robotic ManipulationRobot Foundation ModelsVision-Language-Action ModelsTest-Time ScalingWorld Model-Based Planning
AskPDF
Aug 17, 2026

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively. Moreover, policies trained through offline behavior cloning can remain suboptimal during real-world deployment. Although online reinforcement learning can refine policies through real-world interaction, directly tuning large VLA backbones demands excessive computation and may introduce safety risks during real-robot exploration. To address these bottlenecks, we introduce HAF (Humanoid Adaptation Framework), a two-part framework consisting of HAF-VLA and HAF-Steer that transfers off-the-shelf generalist VLA foundation models to humanoid whole-body loco-manipulation. HAF-VLA is a hierarchical action-flow generator built on a pretrained flow-matching VLA. It splits full-body action denoising into three sequential stages with stage embeddings and cross-stage KV caches that retain kinematic dependencies, avoiding incoherent whole-body actions from one-shot generation. On top of the frozen HAF-VLA, HAF-Steer is a latent offline-to-online RL pipeline that leverages flow-matching invertibility and DCT-based dimensionality reduction to restrict RL optimization to a compact noise subspace and train a regularized SAC policy. This avoids updating the large VLA backbone and enables efficient real-world policy refinement. Evaluated on seven real-world humanoid loco-manipulation tasks, HAF surpasses vanilla single-stage VLA baselines and improves whole-body coordination and task performance. Project website: https://grange007.github.io/HAF .

Langzhe Gu, Chengkai Hou, Meng Li +14

State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · Nankai University +1

Humanoid Loco-ManipulationWhole-Body Robotic ManipulationVision-Language-Action ModelsReinforcement LearningOffline-To-Online RL
AskPDF
Aug 17, 2026

NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation

Real-world deployment of Vision-Language-Action (VLA) models is often bottlenecked by efficiency-performance trade-offs, cross-embodiment generalization, and execution smoothness. We present NebulaVLA, an asynchronous dual-frequency architecture that decouples high-level semantic reasoning from low-level action control, optimizing computational resources and modularity. To bridge semantic gaps across heterogeneous robots, we introduce GESTURE-7, a unified language-grounded action representation. Furthermore, our Guide Action algorithm enforces kinematic continuity via mask-based smoothness constraints. Comprehensive evaluations demonstrate that NebulaVLA significantly outperforms synchronous baselines, achieving an 85.5% average success rate on LIBERO-Plus and accelerating action generation by \textasciitilde 2.7×\times. This asynchronous design enables highly efficient and responsive control for practical robotics.

Cong Zhao, Shuai Tian, Xu Zhang +11

ZTE Corporation China

Vision-Language-Action ModelsEfficient VLA ModelsRobotic ManipulationRobot Motion GenerationCross-Embodiment Robot Learning
AskPDF
Aug 17, 2026

SparkVLA: Stop-Aware Hierarchical VLA with Adaptive Action Chunking for Long-Horizon Manipulation

At every re-observation point in a hierarchical Vision-Language-Action (VLA) system, two interface decisions must be made: when to terminate the current subtask and how far to execute the proposed action chunk. These decisions are mutually dependent---the optimal stopping point depends on what the executor plans to do, while the optimal execution length depends on where the subtask boundary lies---yet existing architectures evaluate them in isolation, an asymmetry neither module can overcome alone. We present SparkVLA, a stop-aware hierarchical VLA that resolves this mutual dependency by formulating both decisions as a single ranking: Stop competes against every action-prefix length in a unified candidate set, and the system selects the highest-scoring option, eliminating threshold tuning and requiring only offline ordinal preferences. An Anchor-Conditioned Context Encoding module caches a history-aware subtask anchor encoding onset-state memory and goal semantics, guiding visual-token pruning toward task-relevant regions; a Stop-Aware Action-Prefix Selection head scores all candidates via full self bnattention at chunk boundaries for efficiency. On RoboCerebra, SparkVLA achieves 47.12% success rate, surpassing the official hierarchical baseline by 30.57% and the strongest reproducible method by 26.83% Real-robot experiments on multi-step tasks further validate these gains on physical hardware.

Xunyao Lei, Renjun Wu, Tianlin Huo +1

Beijing Institute of Technology · Tsinghua University

Vision-Language-Action ModelsLong-Horizon Robotic ManipulationEfficient VLA ModelsAction Chunking
AskPDF
Aug 17, 2026

US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina

Artificial intelligence-assisted ultrasound scanning enhances diagnostic reliability and efficiency by providing real-time guidance for standardized image acquisition and reducing operator dependence. However, existing reinforcement learning and learning-assisted ultrasound scanning methods typically rely on carefully designed reward functions or extensive interaction data, which limits their generalization ability and stability across different devices, patient populations, and complex clinical scenarios. To address these challenges, we propose an ultrasound vision-language-action model (US-VLA) for automated ultrasound scanning that explicitly encodes clinical semantic goals and generates sequential probe manipulation actions under real-time ultrasound feedback. In particular, we first design an ultrasound-aware expert fusion module to jointly integrate ultrasound observations with auxiliary contextual information, enabling semantic ultrasound feedback to effectively guide the scanning process. Then, we construct US-VLA-Data, a real-world dataset covering liver and kidney examinations, which includes five clinically defined standard planes and comprises 320 expert scanning trajectories with approximately 80,000 synchronized timesteps. Extensive experiments demonstrate that US-VLA achieves competitive performance in ultrasound probe manipulation tasks, indicating its effectiveness and promising generalization within the evaluated abdominal ultrasound setting. The source code is available at https://github.com/VMVLab/US-VLA.

Cheng Zhang, Xingzheng Wu, Guihao Yan +4

Innovation School of Artificial Intelligence, Hefei University of Technology Hefei, China

Robotic UltrasoundVision-Language-Action ModelsUltrasound ImagingVLMs for Robotics
AskPDF
Aug 16, 2026

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales pretraining to over 37,000 hours of heterogeneous embodied data, and introduces one-stage alignment training that jointly optimizes vision-language understanding and multi-embodiment action generation. Compared with the preceding GigaBrain-0 series and prior state-of-the-art models including π0.5π_{0.5}, GigaBrain-0.7 achieves substantial improvements in foundation zero-shot capabilities, language-conditioned instruction following, and post-training task success rates. In particular, on our in-house Maker H01 platform and mainstream robot embodiments, GigaBrain-0.7 demonstrates strong task adaptability and completion ability across both home and industrial scenarios. All training code and pretrained model weights will be released.

GigaBrain Team, Angen Ye, Axiang Sun +56

Robot Foundation ModelsVision-Language-Action ModelsCross-Embodiment Robot LearningInstruction Generalization in VLA Models
AskPDF
Aug 16, 2026

ViTaR: Visuo-Tactile Residual Adaptation for Foundation VLA Manipulation

As Vision-Language-Action (VLA) models scale toward real-world deployment, contact-rich manipulation exposes a critical blind spot: these policies encode broad visual-semantic priors yet remain unaware of local contact events, producing identical actions whether contact is established, lost, or destabilized. Existing remedies either modify VLA internals, risking catastrophic forgetting, or demand online reinforcement under near-failure contact conditions. Both grant tactile unbounded influence over action generation, conflicting with the priors that make VLAs generalizable. We introduce ViTaR, which reframes tactile feedback from an action-generating perceptual input to an execution modulator that selects and scales bounded residual corrections atop a frozen VLA, preserving pretrained capabilities by construction. ViTaR decomposes adaptation into two stages: Effect-Guided Modeling determines whether and which correction is locally justified via outcome-grounded preference evidence, and Residual Action Modulation converts this evidence into a residual choice with continuously scaled gain from real-time visuotactile observations. On the UniVTAC benchmark spanning seven contact-rich tasks, ViTaR achieves 61.3% average success, a 30.6 percentage-point improvement over its frozen VLA base that also surpasses purpose-built tactile baselines. Physical-robot experiments confirm that bounded tactile modulation transfers to real sensor noise and dynamics.

Yi Wang, Renjun Wu, Jinyan Liu +1

Beijing Institute of Technology

Contact-Rich Robotic ManipulationVision-Language-Action ModelsTactile Sensing for Robotic ManipulationResidual Policy Learning
AskPDF
Aug 16, 2026

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to 0%0\%, while hundreds of random flips are harmless. Across four model variants spanning three action-head families, damaging bits concentrate in a few action-generating layers, but the empirical budget depends sharply on the head: direct regression and token policies fall in 11--55 flips, whereas the evaluated flow-matching policies require ∼100{\sim}100--300300. Our fixed-direction manifold-escape loss cuts \pizero{}'s budget from ∼1000{\sim}1000 to ∼100{\sim}100 flips, and a matched five-direction sweep shows that the attack is not specific to an all-positive direction. On a direct head, protecting 3.1%3.1\% of weights preserves 60%60\% success at K=100K{=}100, and protecting 5.3%5.3\% moves the open-loop break threshold from 3 to 100 flips. Finally, task-calibrated emulated K=100K{=}100 flips yield 0/200/20 real-robot successes, versus 14/2014/20 clean and 16/2016/20 global-random. Weight integrity is therefore a security boundary for embodied foundation models. Code is included as ancillary material.

Yudong Gao, Linghan Chen, Wenhan Wu +5

The Hong Kong University of Science and Technology · Adelaide University · Wuhan University +3

Adversarial AttacksAdversarial Attacks on VLA ModelsVision-Language-Action ModelsRobustness of VLA Models
AskPDF