mlsanityData to 7 Oct 2026

Training-Time Action Conditioning for Efficient Real-Time Chunking

arXiv 2512.05964 ↗First posted 5 Dec 2025cs.RO cs.AIcited by 61

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

Abstract (arXiv)

Real-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committed actions via inference-time inpainting. However, this inpainting method introduces computational overhead that increases inference latency. In this work, we propose a simple alternative: simulating inference delay at training time and conditioning on action prefixes directly, eliminating any inference-time overhead. Our method requires no modifications to the model architecture or robot runtime, and can be implemented with only a few additional lines of code. In simulated experiments, we find that training-time RTC outperforms inference-time RTC at higher inference delays. In real-world experiments on box building and espresso making tasks with the π0.6 VLA, we demonstrate that training-time RTC maintains both task performance and speed parity with inference-time RTC while being computationally cheaper. Our results suggest that training-time action conditioning is a practical drop-in replacement for inference-time inpainting in real-time robot control.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 23 of its 28 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

23 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference30 Nov
  2. 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunks27 Sep
  3. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Models16 Jan

Other references · 20

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  6. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  7. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  8. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  9. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  10. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  11. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  12. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
8 more
  1. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 298
  2. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  3. 2025π*0.6: a VLA That Learns From Experiencecited by 280
  4. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 201
  5. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  6. 2024ALOHA Unleashed: A Simple Recipe for Robot Dexteritycited by 128
  7. 2023Training-free Linear Image Inverses via Flowscited by 70
  8. 2024Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Taskscited by 40

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 61.

61 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 289
  2. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  3. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  4. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 55
  5. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 42
  6. 2026HoloBrain-0 Technical Reportcited by 20
  7. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  8. 2026Learning Native Continuation for Action Chunking Flow Policiescited by 18
  9. 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perfcited by 17
  10. 2026Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAscited by 8
  11. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 8
  12. 2026FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunkingcited by 8
38 more
  1. 2026AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edgecited by 7
  2. 2026StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observationcited by 6
  3. 2026TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Controlcited by 5
  4. 2026ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulationcited by 5
  5. 2026NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulationcited by 4
  6. 2026πR2: Reactive Real-time Flow Policiescited by 4
  7. 2026World Action Models in Real Time: An Empirical Study of Smooth Execution via Asynchronous Deploymentcited by 4
  8. 2026Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulationcited by 3
  9. 2026DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executorscited by 3
  10. 2026Understanding Asynchronous Inference Methods for Vision-Language-Action Modelscited by 3
  11. 2026Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inferencecited by 3
  12. 2026FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Executioncited by 3
  13. 2026FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inferencecited by 3
  14. 2026SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flowscited by 2
  15. 2026Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Modelscited by 2
  16. 2026Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Modelscited by 2
  17. 2026Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Modelscited by 1
  18. 2026Hermite Curves as Trajectory Priors for Vision-Language-Action Modelscited by 1
  19. 2026You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvementcited by 1
  20. 2026Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latencycited by 1
  21. 2026Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RLcited by 1
  22. 2026FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligencecited by 1
  23. 2026InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Datacited by 1
  24. 2026Long-WAM: Scaling the Context of World-Action Modelscited by 1
  25. 2026Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulationcited by 0
  26. 2026Long-Term Memory for VLA-based Agents in Open-World Task Executioncited by 0
  27. 2026Implicit Action Chunking for Smooth Continuous Controlcited by 0
  28. 2026DexPIE: Stable Dexterous Policy Improvement from Real-World Experiencecited by 0
  29. 2026Real-Time Execution with Autoregressive Policiescited by 0
  30. 2026LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulationcited by 0
  31. 2026Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Reviewcited by 0
  32. 2026A Glimpse into Long-term Physical Coexistence with Intelligent Robotscited by 0
  33. 2026TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Modelcited by 0
  34. 2026RoboFolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objectscited by 0
  35. 2026LieSpline-DP: Lie-Group B-Spline Diffusion Policy for Smooth Robot Manipulationcited by 0
  36. 2026Reinforcement Learning for Real-Time Vision-Language-Action Policiescited by 0
  37. 2026SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulationcited by 0
  38. 2026React When You Need To: Event-Triggered Asynchronous Inference for VLA Policiescited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
  2. 2026DREAM-Chunk: Reactive Action Chunking with Latent World Model
  3. 2026PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
  4. 2026ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning
  5. 2026Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs
  6. 2025VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
  7. 2026When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models
  8. 2026SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies