Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2603.15618v2
• Date: Tue, 17 Mar 2026 16:04:49 GMT
• Title: Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models
• Abstract summary: Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation.<n>We propose textbfDeepVision-VLA, built on a textbfVision-Language Mixture-of-Transformers (VL-MoT) framework.<n>DeepVision-VLA outperforms prior state-of-the-art methods by 9.0% and 7.5% on simulated and real-world tasks, respectively.
• Score: 66.96421290733126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on language instructions. Although recent works have sought to enhance the visual capabilities of VLA models, most approaches treat the LLM backbone as a black box, providing limited insight into how visual information is grounded into action generation. Therefore, we perform a systematic analysis of multiple VLA models across different action-generation paradigms and observe that sensitivity to visual tokens progressively decreases in deeper layers during action generation. Motivated by this observation, we propose \textbf{DeepVision-VLA}, built on a \textbf{Vision-Language Mixture-of-Transformers (VL-MoT)} framework. This framework enables shared attention between the vision foundation model and the VLA backbone, injecting multi-level visual features from the vision expert into deeper layers of the VLA backbone to enhance visual representations for precise and complex manipulation. In addition, we introduce \textbf{Action-Guided Visual Pruning (AGVP)}, which leverages shallow-layer attention to prune irrelevant visual tokens while preserving task-relevant ones, reinforcing critical visual cues for manipulation with minimal computational overhead. DeepVision-VLA outperforms prior state-of-the-art methods by 9.0\% and 7.5\% on simulated and real-world tasks, respectively, providing new insights for the design of visually enhanced VLA models.

Related papers

• AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment [8.122021272122668]
  AffordVLA is an affordance-enhanced Vision-Language-Action (VLA) framework that internalizes manipulation-centric affordance perception into VLA visual representations.<n>We show that AffordVLA effectively reshapes VLA visual representations while preserving inference efficiency, leading to improved manipulation success rates and training efficiency.
  arXiv  Detail & Related papers  (2026-05-17T16:02:05Z)
• Visually-Guided Policy Optimization for Multimodal Reasoning [60.035908460318126]
  We propose Visually-Guided Policy Optimization (VGPO) to reinforce visual focus during policy optimization.<n> VGPO initially introduces a Visual Attention Compensation mechanism that leverages visual similarity to localize and amplify visual cues.<n>We show that VGPO achieves better visual activation and superior performance in mathematical multimodal reasoning and visual-dependent tasks.
  arXiv  Detail & Related papers  (2026-04-10T14:22:38Z)
• VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models [26.542479606920423]
  Vision-Language-Action (VLA) models have demonstrated strong performance across a wide range of robotic manipulation tasks.<n>Despite the success, extending large pretrained VLA models to the action space can induce vision-action misalignment.<n>We propose a training framework that explicitly strengthens visual conditioning in VLA models.
  arXiv  Detail & Related papers  (2026-02-04T20:59:29Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver [35.25196177784228]
  We propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm.<n>Conditioned on the model's visual outputs, a diffusion transformer reconstructs the gaze region of the image.<n>This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention.
  arXiv  Detail & Related papers  (2025-08-14T04:20:19Z)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs)<n>We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens.<n>Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• VinVL: Revisiting Visual Representations in Vision-Language Models [96.39332942534368]
  We develop an improved object detection model to provide object-centric representations of images. New visual features significantly improve the performance across all vision language (VL) tasks. We will release the new object detection model to public.
  arXiv  Detail & Related papers  (2021-01-02T23:35:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.