SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation

• URL: http://arxiv.org/abs/2604.05656v1
• Date: Tue, 07 Apr 2026 09:56:03 GMT
• Title: SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
• Abstract summary: Vision-Language-Action (VLA) models achieve state-of-the-art generalist robotic manipulation.<n>On a modern GPU, denoising alone accounts for 80% of end-to-end inference time.<n>We present SnapFlow, a plug-and-play self-distillation method that compresses multi-step denoising into a single forward pass.
• Score: 18.319705014361908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models based on flow matching -- such as pi0, pi0.5, and SmolVLA -- achieve state-of-the-art generalist robotic manipulation, yet their iterative denoising, typically 10 ODE steps, introduces substantial latency: on a modern GPU, denoising alone accounts for 80% of end-to-end inference time. Naively reducing the step count is unreliable, degrading success on most tasks due to the velocity field being uncalibrated for single-step jumps. We present SnapFlow, a plug-and-play self-distillation method that compresses multi-step denoising into a single forward pass (1-NFE) for flow-matching VLAs. SnapFlow mixes standard flow-matching samples with consistency samples whose targets are two-step Euler shortcut velocities computed from the model's own marginal velocity predictions, avoiding the trajectory drift caused by conditional velocities, as we analyze theoretically. A zero-initialized target-time embedding lets the network switch between local velocity estimation and global one-step generation within a single architecture. SnapFlow requires no external teacher, no architecture changes, and trains in ~12h on a single GPU. We validate on two VLA architectures spanning a 6x parameter range, with identical hyperparameters: on pi0.5 (3B) across four LIBERO suites (40 tasks, 400 episodes), SnapFlow achieves 98.75% average success -- matching the 10-step teacher at 97.75% and slightly exceeding it -- with 9.6x denoising speedup and end-to-end latency reduced from 274ms to 83ms; on SmolVLA (500M), it reduces MSE by 8.3% with 3.56x end-to-end acceleration. An action-step sweep on long-horizon tasks reveals that SnapFlow maintains its advantage across execution horizons, achieving 93% at n_act=5 where the baseline reaches only 90%. SnapFlow is orthogonal to layer-distillation and token-pruning approaches, enabling compositional speedups.

Related papers

• CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models [7.489020109808801]
  We present CrossVLA, an empirical study of cross-paradigm Vision-Language-Action (VLA) post-training.<n>Three contributions: (i) a surrogate flow-matching log-probability estimator that lets DPO operate on continuous-action backbones without probability-flow ODE integration; (ii) a head-to-head comparison of LoRA and DoRA as the parameter-efficient layer for VLA DPO; and (iii) an inference-time anatomy showing the denoise loop dominates 78.6% of sample_actions latency and prefix-K/V caching a la
  arXiv  Detail & Related papers  (2026-05-21T01:02:41Z)
• Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation [50.55853275866995]
  Real-time interactive video generation requires low-latency, streaming, and controllable rollout.<n>In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps.<n>We propose textbfCausal Forcing++, a principled and scalable pipeline.
  arXiv  Detail & Related papers  (2026-05-14T17:46:36Z)
• AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation [70.80207977907908]
  We introduce AnyFlow, the first any-step video diffusion distillation framework based on flow maps.<n>We show that AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime.
  arXiv  Detail & Related papers  (2026-05-13T16:06:34Z)
• Self-Adversarial One Step Generation via Condition Shifting [11.426065945265647]
  APEX is a framework for adversarial correction signals extracted endogenously from a flow model.<n>Our 0.6B model surpasses FLUX-Schnell 12B (20$times$ more parameters) in one step quality.<n>With LoRA tuning on Qwen-Image 20B, APEX reaches a GenEval score of 0.89 at NFE=1 in 6 hours, surpassing the original 50-step teacher (0.87) and providing a 15.33$times$ inference speedup.
  arXiv  Detail & Related papers  (2026-04-14T05:54:33Z)
• EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow [52.73538517981873]
  EFlow is an efficient few-step training framework for video diffusion transformers.<n> Gated Local-Global Attention is a token-droppable hybrid block.<n>Path-Drop Guided training replaces the expensive target with a computationally cheap, weak path.
  arXiv  Detail & Related papers  (2026-03-28T02:06:55Z)
• ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models [12.232846303286161]
  Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manipulation.<n>While current acceleration efforts optimize the Vision-Language Model (VLM) backbone, the action head bottleneck remains overlooked.<n>We propose ProbeFlow, a training-free adaptive inference framework for continuous robotic control.
  arXiv  Detail & Related papers  (2026-03-18T15:38:29Z)
• FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference [10.34801095627052]
  Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower.<n>We propose FastFlow, a plug-and-play adaptive inference framework that accelerates generation in flow matching models.<n> Experiments demonstrate a speedup of over 2.6x while maintaining high-quality outputs.
  arXiv  Detail & Related papers  (2026-02-11T18:21:11Z)
• FlowConsist: Make Your Flow Consistent with Real Trajectory [99.22869983378062]
  We argue that current fast-flow training paradigms suffer from two fundamental issues.<n> conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift.<n>We propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows.
  arXiv  Detail & Related papers  (2026-02-06T03:24:23Z)
• One Step Is Enough: Dispersive MeanFlow Policy Optimization [23.382067451764396]
  Dispersive MeanFlow Policy Optimization (DMPO) is a unified framework that enables one-step generation.<n> Experiments across RoboMimic manipulation and OpenAI Gym locomotion benchmarks demonstrate competitive or superior performance.
  arXiv  Detail & Related papers  (2026-01-28T15:34:29Z)
• ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge [11.016302257907936]
  Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control.<n>Current VLA models operate at only 3-5 Hz on edge devices due to the memory bound nature of autoregressive decoding.<n>We introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge plat forms.
  arXiv  Detail & Related papers  (2025-12-23T11:29:03Z)
• Understanding, Accelerating, and Improving MeanFlow Training [64.84964628592418]
  MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields.<n>We analyze the interaction between the two velocities and find: (i) well-established instantaneous velocity is a prerequisite for learning average velocity.<n>We design an effective training scheme that accelerates the formation of instantaneous velocity, then shifts emphasis from short to long-interval average velocity.
  arXiv  Detail & Related papers  (2025-11-24T12:59:27Z)
• MeanFlowSE: one-step generative speech enhancement via conditional mean flow [13.437825847370442]
  MeanFlowSE is a conditional generative model that learns the average velocity over finite intervals along a trajectory.<n>On VoiceBank-DEMAND, the single-step model achieves strong intelligibility, fidelity, and perceptual quality with substantially lower computational cost than multistep baselines.
  arXiv  Detail & Related papers  (2025-09-18T11:24:47Z)
• Next Block Prediction: Video Generation via Semi-Autoregressive Modeling [92.60177942930946]
  Next-Block Prediction (NBP) is a semi-autoregressive (semi-AR) framework for video generation.<n>NBP employs bidirectional attention within each block, enabling tokens to capture more robust spatial dependencies.<n>Our model achieves FVD scores of 103.3 on UCF101 and 25.5 on K600, outperforming the vanilla NTP model by an average of 4.4.
  arXiv  Detail & Related papers  (2025-02-11T17:57:53Z)
• Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner [112.99126045081046]
  A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed.<n>We propose a textbftimestep tuner that helps find a more accurate integral direction for a particular interval at the minimum cost.<n>Experiments show that our plug-in design can be trained efficiently and boost the inference performance of various state-of-the-art acceleration methods.
  arXiv  Detail & Related papers  (2023-10-14T02:19:07Z)

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.