mlsanityData to 14 Oct 2026

SMILE: Smooth Motion for Improved Long-Horizon VLA Execution

arXiv 2608.29432 ↗First posted 29 Aug 2026cs.ROcited by 0

On the map: Vision-language-action models → Efficient VLA inference and adaptation

Abstract (arXiv)

Vision-Language-Action (VLA) models reduce inference cost by executing multiple actions per call, but longer horizons often degrade accuracy because raw chunks contain jitter and outliers. We introduce SMILE, an architecture-preserving interface that predicts B-spline coefficients and decodes them into smooth action sequences. SMILE changes only the action representation, enabling longer fixed horizons while retaining each baseline's backbone and model scale. We apply SMILE to SmolVLA, Evo1, VPP, and DAWN, improving accuracy and amortized inference efficiency across LIBERO, CALVIN, and real-world experiments. SMILE-Evo1 reaches 98.0% with a 1.1x speedup on LIBERO, while SMILE-VPP reaches an average length of 4.42 with a 1.5x speedup on CALVIN. At a matched execution horizon of 10, SMILE-SmolVLA reduces non-boundary acceleration by 78.6% and velocity sign-change rate by 42.3%. Real-world xArm tests show higher success, fewer drops, and fewer contacts. These results establish smooth coefficient-space generation as a route to accurate, efficient long-horizon VLA execution. Project page: jongwoopark7978.github.io/smilevla

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 26 of its 28 references that are in the map. First posted on arXiv 29 Aug 2026.

Builds on

26 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Models5 Apr
  2. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process3 Nov
  3. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Models16 Jan

Other references · 23

  1. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  6. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  7. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  8. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  9. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 289
  10. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasetscited by 240
  11. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  12. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
11 more
  1. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 195
  2. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 161
  3. 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulatorscited by 64
  4. 2024Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Samplingcited by 52
  5. 2024VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulationcited by 46
  6. 2025Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignmentcited by 41
  7. 2025BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learningcited by 27
  8. 2026ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulationcited by 10
  9. 2025Pixel Motion Diffusion is What We Need for Robot Controlcited by 7
  10. 2026Spline Policy: A Structured Representation for Robot Policiescited by 5
  11. 2026B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representationscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026FASTER: Rethinking Real-Time Flow VLAs
  2. 2025ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
  3. 2026Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
  4. 2026FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference
  5. 2026CARE: Certifying Acceleration for Vision-Language-Action Inference
  6. 2026Accelerating VLA Inference with Perturbation Informed Execution
  7. 2025Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
  8. 2026A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model