ICML 2026 Papers

Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations more closely with the robot's proprioceptive states by using relative distances between the states as soft supervision. Complementing the original action prediction objective, RS-CL enhances control-relevant representation learning, while being lightweight and fully compatible with standard VLA training pipelines. Our empirical results demonstrate that RS-CL substantially improves the performance of state-of-the-art VLA models; it pushes the prior art to 69.7% achieving the state-of-the-art performance on the RoboCasa-Kitchen benchmark, and boosts success rates from 45.0% to 58.3% on challenging real-robot manipulation tasks.

Reinforcement learning often produces high-frequency oscillatory control signals that undermine the safety and stability required for physical deployment. Explicit action chunking addresses this by predicting fixed-horizon trajectories but scales the policy output dimension proportionally with the horizon length, leading to optimization difficulties and incompatibility with standard step-wise interaction. To overcome these challenges, this paper proposes Dual-Window Smoothing (DWS), an implicit action chunking framework for smooth continuous control. Unlike explicit methods, DWS enforces temporal coherence without expanding the action space. It uses a dual-window design: an execution window that ensures physical smoothness through deterministic modulation, and a value window that aligns temporal-difference targets over the horizon to correct critic bias caused by open-loop execution. DWS also includes a lightweight actor-side temporal regularizer based on first-order action differences to promote global continuity. This design effectively bridges the gap between temporal abstraction and reactive step-wise control. Experiments on benchmarks including the DeepMind Control Suite and industrial energy management tasks show that DWS outperforms state-of-the-art (SOTA) baselines. In complex vision-based autonomous driving tasks, DWS achieves smoother control, safer behavior with reduced jitter, and attains a 100% success rate.

Vision–Language–Action (VLA) models adapt large vision–language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions autoregressively in a fixed left-to-right order with poor performance or attach separate diffusion heads outside the backbone that fragments information pathways and hinders unified, scalable architectures. Instead, we present Discrete Diffusion VLA that discretizes action chunks and models them with discrete diffusion pattern retaining progressive refinement inside the unified transformer backbone. Our method achieves an adaptive decoding order that resolves high-confidence action elements before harder ones and employs secondary re-masking to revisit uncertain predictions, enabling robust error correction. This design preserves pretrained vision-language priors, supports parallel decoding, and improves the efficiency. Discrete Diffusion VLA achieves 96.4% avg. success on LIBERO, 71.2% visual matching on SimplerEnv-Fractal, and 54.2% overall on SimplerEnv-Bridge. On out-of-distribution tests of LIBERO-Goal, our method exhibits only 0.8% language degradation versus 8.0% of parallel decoding, and 20.4% vision degradation versus 29.0% for continuous diffusion, demonstrating well retention of pretrained vision-language capabilities. We also conduct two real-robot evaluations on AgileX Cobot Magic platform to show the method's effectiveness.

Bridging high-level semantic understanding with low-level physical control remains a persistent challenge in embodied intelligence, stemming from the fundamental spatiotemporal scale mismatch between cognition and action. Existing generative VLA policies typically adopt a "Generation-from-Noise" paradigm, which disregards this disparity, leading to representation inefficiency and weak condition alignment during optimization. In this work, we propose ResVLA, an architecture that shifts the paradigm to "Refinement-from-Intent." Recognizing that robotic motion naturally decomposes into global intent and local dynamics, ResVLA utilizes spectral analysis to decouple control into a deterministic low-frequency anchor and a stochastic high-frequency residual. By anchoring the generative process on the predicted intent, our model focuses strictly on refining local dynamics via a residual diffusion bridge. Extensive simulation experiments show that ResVLA achieves competitive performance, strong robustness to language and robot embodiment perturbations, and faster convergence than standard generative baselines. ResVLA also demonstrates strong performance in real-world robot experiments.

Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal consistency at moderate action frequencies, it becomes insufficient when the action frequency is further increased (e.g., to 60~Hz). At such high frequencies, policies often fail to generate actions that are both temporally smooth and spatially consistent. We address this challenge by shifting high-frequency action learning from the action space to a latent space with variational autoencoder (VAE). This formulation significantly improves both temporal and spatial consistency of high-frequency control. To enable smooth real-time execution, we further introduce Reuse-then-Refine, a chunk-level refine strategy that improves continuity between adjacent action chunks under asynchronous inference. As a result, robots controlled by our policy can execute complex contact-rich tasks continuously, with less pauses and jerky motions. Experiments on three real-world contact-rich robotic tasks show that our approach consistently completes tasks with smooth motions. Our code and data are available at https://github.com/tars-robotics/RTR.

Prompt learning for vision-language models (VLMs) primarily follows end-to-end or decoupled routes to balance base and new task performance, but suffers a fundamental bottleneck: sample-wise optimization within task-specific feature spaces traps models in local optima, hindering global optimality. To address this, we identify a key insight that VLMs can be prompted within a Coupled Prompt Field-a shared space where base and new tasks are mutually constrained-and present AlignedNorm, which enforces the field coupling. By dynamically aligning the norms of prompts to VLMs' native scale, our method enables joint optimization of both tasks. Without complex designs, our method matches leading decoupled approaches on 15 datasets across 4 experimental settings, offering both a new perspective and a practical solution to the local-optima dilemma in prompt learning.

It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models when encountering unseen real-world visual disturbances, particularly under imperfect visual conditions. In this work, we conduct a systematic study based on recent state-of-the-art VLA models and reveal a significant performance drop when visual disturbances absent from the training data are introduced. To mitigate this issue, we propose a lightweight adapter module grounded in information theory, termed the Information Bottleneck Adapter (IB-Adapter), which selectively filters potential noise from visual inputs. Without requiring any extra data or augmentation strategies, IB-Adapter consistently improves over the baseline by an average of 30%, while adding fewer than 10M parameters, demonstrating notable efficiency and effectiveness. Furthermore, even with a 14x smaller backbone (0.5B parameters) and no pre-training on the Open X-Embodiment dataset, our model StableVLA achieves robustness competitive with 7B-scale state-of-the-art VLAs. With negligible parameter overhead (<10M), our approach maintains accuracy on long-horizon tasks and surpasses OpenPi under real-world visual disturbances. The code will be made publicly available.

Knowledge distillation is crucial for compressing large Vision–Language Models (VLMs) into efficient architectures. While prior VLM research has primarily focused on reasoning tasks like visual question answering, multimodal embedding learning, a key component for large-scale retrieval, has received comparatively less attention. Existing distillation methods typically align static global representations, overlooking hierarchical feature structure and fine-grained cross-modal interactions. This leads to a structural gap where student models fail to inherit object-level semantics and spatial relationships from teachers. To address this limitation, we propose **HieRD**, a Hierarchical Representation Distillation framework that preserves hierarchical structure within and across modalities throughout the distillation process by leveraging clustered visual tokens and multi-granular alignment with phrase-level text. Experimental results on multimodal embedding and downstream tasks show that HieRD consistently outperforms strong baselines, reflecting the effectiveness of its fine-grained semantic and spatial modeling, while enabling compact and efficient embedding models.

This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the $\textit{minimum action distance}$ (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. The MAD naturally enables critical downstream tasks such as goal-conditioned reinforcement learning and reward shaping by providing a dense, geometrically meaningful measure of progress. Our self-supervised learning approach constructs an embedding space where the distances between embedded state pairs correspond to their MAD, accommodating both symmetric and asymmetric approximations. We evaluate the framework on a comprehensive suite of environments with known MAD values, encompassing both deterministic and stochastic transition dynamics, discrete and continuous state spaces, and environments with noisy observations. Empirical results show that the proposed approach learns MAD representations more efficiently than existing methods, produces more accurate estimates of the true MAD, and improves performance on downstream goal-reaching tasks.

While Large Vision-Language Models (LVLMs) achieves remarkable success, hallucinations remain a significant barrier to their reliable deployment. Recent studies primarily attribute these defects to cross-modal attention imbalances, with most solutions focusing on re-weighting visual tokens or suppressing language priors. Such approaches often overlook the spectral characteristics of the visual information flow and frequently rely on Contrastive Decoding (CD), which doubles the inference time. Instead of following conventional approaches, we identify two distinct hallucination patterns—Perceptual-Semantic Dissociation and Localized Fixation—and accordingly develop FLASH (Frequency-Localized Attention SHaping), a training-free and CD-free framework. FLASH utilizes a Spectral Vortex Score to detect visual heads within multi-head attention layers, applying adaptive spectral modulation to rectify the visual information flow during the decoding phase. Empirical results demonstrate that FLASH offers a superior balance between performance and efficiency compared to SOTA methods.

Vision-Language Models (VLMs) achieve remarkable performance on multimodal tasks but remain highly vulnerable to adversarial examples, making transferable attacks essential for realistic robustness evaluation. Recent Adversarial Evolution Triangle (AET) methods improve transferability by interpolating over a simplex formed by clean and historical adversarial samples, yet rely on finite random sampling to approximate effective perturbation distributions, which is unstable under limited budgets. In this paper, we propose Dirichlet Distributional Gradient Aggregation (DDGA), a distribution-aware adversarial attack framework that explicitly models and optimizes perturbations over the AET simplex. DDGA parameterizes simplex mixing weights with a learnable Dirichlet policy and optimizes the expected adversarial objective via policy gradient, replacing heuristic sampling with principled distributional optimization. Moreover, we exploit the closed-form covariance of the learned distribution to construct orthogonal perturbations that enhance gradient diversity. Extensive experiments on image-text retrieval and image captioning demonstrate that DDGA consistently outperforms state-of-the-art transfer-based attacks across multiple VLM architectures.

Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from over-conservatism that suppresses high-value actions in the distribution tail; conversely, gradient-based approaches often exhibit a fitting-optimization conflict of gradients, which drive the policy off the data manifold. To address this, we propose \textbf{S}upport-\textbf{P}reserving \textbf{A}ction \textbf{R}ectification (SPAR), which reframes global learning as a local residual rectification anchored to a frozen pure behavior cloning policy. This framework performs fine-grained fitting and local policy improvement in the residual space, thereby contracting the search space. We further introduce Latent Self-Imitation, utilizing a latent-sampling weighted-regression mechanism to address fitting-improvement gradient conflict in the residual space. Theoretically, we prove this mechanism eliminates the manifold-normal drift of standard value gradients, while extensive D4RL experiments show SPAR extracts significant gains from suboptimal baselines to achieve state-of-the-art performance.

Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields inference-time physical plausibility checks. We propose Scrambled Edges, a controlled counterfactual that injects salient edge-like cues while violating surface continuity, illumination coherence, and occlusion ordering. With energy-matched and structure-matched controls, we isolate the effect of unsupported edge evidence from high-frequency energy and edge sparsity. Across CNN/ViT/SSL depth predictors on NYU Depth v2 and KITTI, Scrambled Edges induce up to 3.2× larger deviation from clean predictions than energy-matched noise. The resulting Geometric Collapse propagates globally: even with oracle knowledge of the corrupted region, output-level repair recovers only 47%, with substantial error outside the mask. These findings provide controlled behavioral evidence that current dense predictors lack reliable mechanisms to quarantine physically unsupported edge cues, motivating explicit plausibility scoring and selective cue integration.

We introduce \textit{ImmersePro}, an innovative framework specifically designed to transform single-view videos into stereo videos. This framework utilizes a novel dual-branch architecture comprising a disparity branch and a context branch on video data by leveraging spatial-temporal attention mechanisms. \textit{ImmersePro} employs implicit disparity guidance, enabling the generation of stereo pairs from video sequences without the need for explicit disparity maps, thus reducing potential errors associated with disparity estimation models. In addition to the technical advancements, we introduce the YouTube-SBS dataset, a comprehensive collection of 423 stereo videos sourced from YouTube. This dataset is unprecedented in its scale, featuring over 7 million stereo pairs, and is designed to facilitate training and benchmarking of stereo video generation models. Our experiments demonstrate the effectiveness of \textit{ImmersePro} in producing high-quality stereo videos, offering significant improvements over existing methods. Compared to the best competitor stereo-from-mono we quantitatively improve the results by 11.76\% (L1), 6.39\% (SSIM), and 5.10\% (PSNR).

With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality of editing highly depends on carefully designed instructions, placing the burden of task decomposition and sequencing entirely on the user. To achieve autonomous image editing, we present PhotoAgent, a system that advances image editing through explicit aesthetic planning. Specifically, PhotoAgent formulates autonomous image editing as a long-horizon decision-making problem. It reasons over user aesthetic intent, plans multi-step editing actions via tree search, and iteratively refines results through closed-loop execution with memory and visual feedback, without requiring step-by-step user prompts. To support reliable evaluation in real-world scenarios, we introduce UGC-Edit, an aesthetic evaluation benchmark consisting of 7,000 photos and a learned aesthetic reward model. We also construct a test set containing 1,017 photos to systematically assess autonomous photo editing performance. Extensive experiments demonstrate that PhotoAgent significantly outperforms existing methods in both instruction faithfulness and visual quality across a diverse range of editing scenarios.

We investigate which architectural and input-pipeline choices make vision models more robust to additive Gaussian noise and convert these empirical insights into simple, actionable design rules. Specifically, we performed extensive evaluations on 1,174 pretrained vision models, empirically identifying four consistent factors for improved robustness against Gaussian noise: larger stem kernels, resolution-dependent downsampling under a pre-resize sensor-noise protocol, average pooling, and supervised vision transformers (ViTs) rather than CLIP ViTs, which yield up to 506 rank improvements and 21.6\%p accuracy gains. First, we prove that low-pass stem kernels attenuate noise with a gain that decreases quadratically with kernel size and that anti-aliased downsampling reduces noise energy roughly in proportion to the square of the downsampling factor. Second, we demonstrate that average pooling is unbiased and suppresses noise in proportion to the pooling window area, whereas max pooling incurs a positive bias that grows slowly with window size and yields a relatively higher mean-squared error and greater worst-case sensitivity. Third, we reveal and explain the vulnerability of CLIP ViTs via a pixel-space Lipschitz bound: The smaller normalization standard deviations used in CLIP preprocessing amplify worst-case sensitivity by up to 1.91 times relative to the Inception-style preprocessing common in supervised ViTs. Our results collectively disentangle robustness into interpretable modules, provide a theory that explains the observed trends, and build practical, plug-and-play guidelines for designing vision models more robust against Gaussian noise.

Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively small behavior cloning (BC) policy models trained from scratch, its behavior in modern large-scale pretrained Vision-Language-Action (VLA) models remains underexplored. In this work, we find that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch. Simple Experience Replay (ER) works surprisingly well on VLAs, sometimes achieving zero forgetting even with a small replay data size. Our analysis reveals that pretraining plays a critical role in downstream continual learning performance: large pretrained models mitigate forgetting with a small replay buffer size while maintaining strong forward learning capabilities. Furthermore, we find that VLAs can retain relevant knowledge from prior tasks despite performance degradation during learning new tasks. This knowledge retention enables rapid recovery of seemingly forgotten skills through finetuning. Together, these insights imply that large-scale pretraining fundamentally changes the dynamics of continual learning, enabling models to continually acquire new skills over time with simple replay.

Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and lack a systematic comparison. This work structures the study of latent action supervision from two perspectives: (i) regularizing the trajectory via image-based latent actions, and (ii) unifying the target space with action-based latent actions. Under a unified VLA baseline, we instantiate and compare four representative integration strategies. Our results reveal a formulation-task correspondence: image-based latent actions benefit long-horizon reasoning, whereas action-based latent actions excel at complex motor coordination. Furthermore, we find that directly supervising the VLM with discrete latent action tokens yields the most effective performance. Finally, our experiments offer initial insights into the benefits of latent action supervision in mixed-data, suggesting a promising direction for VLA training.

Vision-Language-Action models have recently shown promising progress in embodied robotic manipulation, yet their generalization to diverse open-ended embodied tasks is often hindered by execution failures. While prior work has explored failure handling, existing approaches still suffer from two fundamental limitations: coarse-grained failure correction and unreliable failure prevention. These limitations lead to brittle decision-making when VLA models are deployed in novel tasks and environments. To address them, we propose NeurVLA, a neural-symbolic framework that jointly addresses failure correction and prevention via neural-symbolic reasoning and further internalizes these failure-handling capabilities into VLA models. Experiments demonstrate that NeurVLA achieves strong performance and robust generalization across diverse tasks.