Papers
Topics
Authors
Recent
Search
2000 character limit reached

Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models

Published 4 Jun 2026 in cs.CV, cs.AI, cs.LG, and cs.RO | (2606.05737v1)

Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising. We argue that VLA action generation has a different condition-target structure: the policy is conditioned on rich observations, language, and state, but predicts only a compact, low-dimensional action chunk. Under this asymmetry, strong one-step action generation should not necessarily require the advanced one-step methods developed for image synthesis. We keep standard velocity prediction and add no teacher model, distillation stage, or auxiliary objective; in our main recipe, we simply bias the training time distribution toward high-noise states. We first isolate the effect in a controlled MNIST grid-to-sequence task, then test it with extensive robot-policy experiments. Across standard LIBERO, LIBERO-Plus, and LIBERO-Pro, one-step policies trained with high-noise biased schedules generally match ten-step decoding under the same recipe, and on standard LIBERO can exceed ten-step policies trained with a uniform time distribution. A real-robot bimanual YAM RSS evaluation gives a small-sample cross-architecture check of the same sampler trend. On a 1.4B VLM model with a 30M action head, one-step decoding reaches 95.6\% on LIBERO-Long. These results show that strong one-step VLA action generation can emerge from standard diffusion training, without importing the full few-step diffusion machinery developed for image generation.

Summary

  • The paper demonstrates that a 1.4B vision-language model with a 30M action head achieves 95.6% one-step success on LIBERO-Long using standard conditional flow matching without distillation or auxiliary losses.
  • The method shifts training toward high-noise states, improving one-step performance because rich visual, language, and proprioceptive conditions constrain the compact action target more effectively than image-generation conditions constrain pixels.
  • The results across LIBERO, LIBERO-Plus, LIBERO-Pro, and limited real-robot tests show that one-step decoding can match or exceed ten-step inference, while performance remains sensitive to action horizon and noise-shift selection.

Overview

This paper examines whether diffusion-based vision-language-action (VLA) models actually need the multi-step denoising machinery that has become standard in image generation. The authors' central claim is that VLA action generation occupies a different condition-target regime than image synthesis: the model is conditioned on rich observations (camera images, language prompts, proprioceptive state) but predicts only a compact, low-dimensional action chunk of tens to a few hundred scalars. Under this asymmetry, they argue, strong one-step action generation should emerge from standard conditional flow matching without consistency training, distillation, teacher models, or auxiliary objectives (2606.05737). Their main intervention is remarkably simple: bias the training time distribution toward high-noise states.

The paper's strongest headline result is that a 1.4B VLM backbone with a 30M-parameter action head reaches 95.6% success on LIBERO-Long with one-step decoding, using only the standard velocity-prediction objective. This directly challenges the intuition that diffusion policies require many solver steps and that few-step generation requires importing the image-generation toolkit (consistency models, distribution matching distillation, shortcut models, mean flows, flow maps).

The condition-target argument

The authors frame the problem by analogy: text-to-image generation has a weak condition (a prompt) and a high-dimensional multimodal target, which is why one-step methods there require extra machinery. VLA action generation is structurally closer to image-to-text: a rich condition largely determines a compact structured target. When the condition encoder already provides a useful scene and task representation, the remaining conditional action distribution can be simple enough that the population-optimal velocity field—the conditional mean velocity—yields a good one-step prediction directly.

They isolate this structure in a controlled MNIST grid-to-sequence probe: given a 4×44\times4 grid of MNIST digits, generate the corresponding 16-token digit sequence under continuous diffusion for language modeling. Shifting training toward high-noise states substantially improves exact-match accuracy, most clearly for one-step decoding. Diagnostic ablations reinforce the interpretation: stronger visual encoders raise the performance ceiling, larger decoders do not compensate for weak visual features, and pure-noise training is far less effective on a CIFAR-10 class-to-image control where the condition is weaker and the target high-dimensional. Notably, an autoregressive baseline on the toy task needs roughly double the model scale to match the diffusion model's exact-match accuracy.

Method

Training uses standard conditional flow matching with linear interpolation between noise (t=0t=0) and data (t=1t=1), constant target velocities, and the usual squared-error loss against x1−x0x_1 - x_0. The only modification is a noise shift applied to sampled times,

t=u1+(α−1)(1−u),α>1,t = \frac{u}{1 + (\alpha-1)(1-u)}, \qquad \alpha > 1,

which biases samples toward the noise endpoint where one-step inference begins. As a stress test they also evaluate pure-noise training—replacing interpolated inputs with independent Gaussian noise and predicting clean actions from the condition alone—which serves as a diagnostic of how simple the conditional action target is.

The architecture follows the lightweight-head direction of SimVLA: a PaliGemma/SigLIP vision-language encoder produces condition tokens, and a shallow bidirectional Transformer action head (4 layers, width 768) predicts velocities from condition tokens, robot state, time embeddings, and noised action tokens. Two scales are used: a tiny sliced-encoder model for controlled ablations and a full-encoder model for validation.

Results on LIBERO-family benchmarks

On standard LIBERO (all four suites, 50 episodes per task), the time-schedule ablation at horizon 10 shows a clear trade-off. With α=4\alpha=4, one-step decoding reaches 96.4/99.6/96.8/85.2% across Spatial/Object/Goal/Long, exceeding uniform ten-step decoding on every suite; however, the same high-noise bias degrades ten-step decoding substantially (e.g., Long drops to 63.4%), and α=8\alpha=8 collapses ten-step performance almost entirely. The practical implication is that the schedule must be chosen to match the intended inference budget—one-step and ten-step regimes prefer different time distributions.

Action-horizon ablations delineate the boundary of the effect. At H20/H30 on LIBERO-Long, high-noise schedules recover much of the one-step loss relative to uniform sampling and approach or exceed the uniform ten-step reference. At H40 the gap reopens (one-step 44.6% vs. ten-step 53.4% under uniform), indicating that very long open-loop chunks are harder to collapse into a single endpoint prediction. The authors are explicit that this is boundary evidence, not a universal recipe.

Condition ablations support the causal story: removing any input source hurts one-step success, and removing proprioceptive state nearly destroys the policy (0.0–0.4% across suites). The full-encoder runs confirm one-step decoding remains strong at scale—e.g., 98.4/100.0/97.0/95.6% with full32 supervision—without distillation or auxiliary losses.

Beyond standard LIBERO, the results generalize along two axes:

  • LIBERO-Plus (2000 episodes per suite): all 18 comparable recipes lie on or above the one-step versus ten-step diagonal, with a mean one-step margin of +5.4 success points; the largest single margin is +15.5 points (H40, α=4\alpha=4).
  • LIBERO-Pro robustness probing: a checkpoint trained only on standard LIBERO shows essentially identical sampler trends under perturbation (44.2% mean one-step vs. 43.5% ten-step), though absolute robustness varies sharply by perturbation type—language swaps are handled well (82.6% mean) while object-swap and task-change cells fall near zero.
  • Real-robot bimanual YAM RSS: fine-tuned π0.5\pi_{0.5} policies evaluated with only the number of inference steps changed show one-step matching or beating ten-step decoding on all three tasks, including 100% vs. 50% on Tower of Hanoi. The authors correctly flag this as a small-sample check (five trials per cell).

Velocity-field diagnostics

To explain why one-step decoding works, the authors inspect the learned velocity field along noise-data interpolations. Across simulated and real-robot policies, MSE and cosine error decrease monotonically toward the noise endpoint—the point where one-step inference starts—whereas a CIFAR-10 class-to-image flow exhibits lowest error mid-trajectory. This provides mechanistic evidence consistent with the condition-target view: when the condition determines the target, the velocity field is most accurate exactly where one-step decoding needs it. The authors concede, however, that this explanation remains mostly intuitive rather than formally established.

Limitations and open questions

Two limitations are stated plainly. First, the theoretical account is incomplete: it remains unexplained why conditional variance behaves differently near the noise endpoint for compact-target tasks than for image generation. Second, there is no principled procedure for selecting the shift parameter α\alpha for a new horizon, condition set, or execution protocol—the paper relies on empirical sweeps, and the sensitivity of results to this choice (including catastrophic ten-step degradation at aggressive shifts) means practitioners cannot yet pick schedules a priori. Additional caveats include the small-sample nature of the real-robot evaluation, the fact that replanning frequency materially affects closed-loop success independently of flow-step count, and the observation that deeper action heads bring no consistent gain while sometimes destabilizing multi-step decoding.

Conclusion

This paper demonstrates that strong one-step VLA action generation can arise from vanilla flow-matching training with a biased time distribution, provided the condition-target structure is favorable—a rich observation-language-state condition paired with a compact action chunk. The evidence spans controlled toy probes, extensive LIBERO-family simulation, and a cross-architecture real-robot check, with the headline result of 95.6% one-step success on LIBERO-Long at modest action-head scale. The practical message is that before adopting distillation-based few-step machinery from image generation, VLA design should first exploit the structural simplicity of action generation. The open questions—principled schedule selection and a formal account of the endpoint-concentrated velocity accuracy—are well posed and specific to the mechanism the paper identifies.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.