From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2605.04678v1
• Date: Wed, 06 May 2026 09:27:07 GMT
• Title: From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
• Abstract summary: We study 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.<n>Our results reveal a formulation-task correspondence, whereas action-based latent actions excel at complex motor coordination.
• Score: 14.109112325287208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 and scene-level generalization, 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. Code is available at https://github.com/RUCKBReasoning/From_Pixels_to_Tokens.

Related papers

• ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning [53.17987412112712]
  Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks.<n>In this work, we first investigate the exploration stagnation bottleneck in current VLA-RL frameworks.<n>We introduce RL Exploration Token (ExToken), a simple yet general framework that condition VLA policies on discrete behavioral priors.
  arXiv  Detail & Related papers  (2026-07-14T16:04:41Z)
• CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models [22.159641172687884]
  Vision-Language-Action (VLA) models have become a promising paradigm for generalist robot manipulation.<n>We propose CAC-VLA, a Context-Gated Action Conditioning framework that learns a lightweight latent-action interface directly within the VLM.<n>Experiments on LIBERO and LIBERO-Plus demonstrate the effectiveness of CAC-VLA, achieving 98.3% average success rate.
  arXiv  Detail & Related papers  (2026-07-06T08:50:05Z)
• QuoVLA: Quotient Space for Vision-Language-Action Models [51.02329790939691]
  Vision-Language-Action (VLA) models commonly adapt pretrained VLM latents to robot control by mapping visual observations and language instructions to continuous actions.<n>Our textitQuotient Theory for VLA shows that pretrained VLM latents are not action-insufficient but action-sufficient.<n>We propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations.
  arXiv  Detail & Related papers  (2026-05-24T06:28:53Z)
• Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance [108.46436073194546]
  We argue that effective planning should be local, visually grounded, internally generated, and directly aligned with action.<n>We propose Afford-VLA, a unified framework that internalizes task-conditioned affordance as an explicit visual planning interface within VLA models.
  arXiv  Detail & Related papers  (2026-05-22T20:43:47Z)
• Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models [15.486973209713954]
  GTA-VLA(Guide, Think, Act) is an interactive Vision-Language-Action framework.<n>It enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues.
  arXiv  Detail & Related papers  (2026-05-13T14:58:29Z)
• GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization [101.37117235471709]
  We introduce GuidedVLA, a framework designed to guide the action generation to focus on task-relevant factors.<n>Our core insight is to treat the action decoder not as a monolithic learner, but as an assembly of functional components.<n>Our results suggest that explicitly guiding action-decoder learning is a promising direction for building more robust and general VLA models.
  arXiv  Detail & Related papers  (2026-05-12T16:38:40Z)
• LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment [19.95295518800639]
  General visual foundation models consistently outperform specialized embodied latent action models.<n>Latent-based visual space is better aligned to physical action space than pixel-based space.
  arXiv  Detail & Related papers  (2026-04-13T16:30:35Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models [69.58413440457828]
  Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead.<n>We propose Latent Reasoning VLA (textbfLaRA-VLA), a unified VLA framework that internalizes multi-modal CoT reasoning into continuous latent representations for embodied action.
  arXiv  Detail & Related papers  (2026-02-01T11:34:37Z)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• iFlyBot-VLA Technical Report [25.330744626382977]
  We introduce iFlyBot-VLA, a large-scale Vision-Language-Action (VLA) model trained under a novel framework.<n>The main contributions are listed as follows: (1) a latent action model thoroughly trained on large-scale human and robotic manipulation videos; (2) a dual-level action representation framework that jointly supervises both the Vision-Language Model (VLM) and the action expert during training; and (3) a mixed training strategy that combines robot trajectory data with general QA and spatial QA datasets.
  arXiv  Detail & Related papers  (2025-11-01T06:24:56Z)
• Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization [42.41263928527529]
  Vision-Language-Action (VLA) models can endow agents with transferable world knowledge and vision-language grounding.<n>Yet when these VLMs are adapted to the action modality, it remains unclear to what extent their original visual representations and knowledge are preserved.<n>We conduct a systematic study of representation retention during VLA fine-tuning, showing that naive action fine-tuning leads to degradation of visual representations.
  arXiv  Detail & Related papers  (2025-10-29T15:20:10Z)
• 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)
• Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives [89.34229413345541]
  We propose a conditioning scheme which avoids pitfalls by learning the controller and its conditioning in an end-to-end manner. Our model predicts complex action sequences based directly on a dynamic image representation of the robot motion. We report significant improvements in task success over representative MPC and IL baselines.
  arXiv  Detail & Related papers  (2020-03-19T15:04:37Z)

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.