PAINT reframes asynchronous flow-based action chunking as an initial noise selection problem solved via backward Euler inversion and a repainting rule.
FASTER: Rethinking Real-Time Flow VLAs
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smoothness, but neglect the critical latency in reacting to environmental changes. By rethinking the notion of reaction in action chunking policies, this paper presents a systematic analysis of the factors governing reaction time. We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon. Moreover, we reveal that the standard practice of applying a constant schedule in flow-based VLAs can be inefficient and forces the system to complete all sampling steps before any movement can start, forming the bottleneck in reaction latency. To overcome this issue, we propose Fast Action Sampling for ImmediaTE Reaction (FASTER). By introducing a Horizon-Aware Schedule, FASTER adaptively prioritizes near-term actions during flow sampling, compressing the denoising of the immediate reaction by tenfold (e.g., in $\pi_{0.5}$ and X-VLA) into a single step, while preserving the quality of long-horizon trajectory. Coupled with a streaming client-server pipeline, FASTER substantially reduces the effective reaction latency on real robots, especially when deployed on consumer-grade GPUs. Real-world experiments, including a highly dynamic table tennis task, prove that FASTER unlocks substantially improved real-time responsiveness for generalist policies, enabling rapid generation of accurate and smooth trajectories.
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
DAM-VLA decouples per-modality temporal processing in vision-language-action models via latent buffers refreshed at sensor rates, achieving 95.2% average success versus 40.95% for synchronous baselines on seven real-world manipulation tasks while enabling 100 Hz control.
vla.cpp is a unified C++ runtime that serves multiple VLA architectures with flow-matching and diffusion patterns, matching SOTA performance on LIBERO while running on low-memory embedded hardware.
DEFLECT is an offline post-training method that improves async VLA policy success rates under high inference delays by using flow-matching likelihood ratios on counterfactual fresh/stale action pairs from a frozen reference policy.
ElegantVLA accelerates VLA models up to 3.77x by dynamically scheduling compute across vision, language, and action components without retraining the base model.
LiteVLA-H delivers 19.74 Hz action tokens and 6 Hz semantic outputs on Jetson Orin via dual-rate scheduling and mixed fine-tuning, outperforming recent VLA baselines in edge action rate while preserving descriptive competence.
citing papers explorer
-
Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection
PAINT reframes asynchronous flow-based action chunking as an initial noise selection problem solved via backward Euler inversion and a repainting rule.
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
-
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
-
DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model
DAM-VLA decouples per-modality temporal processing in vision-language-action models via latent buffers refreshed at sensor rates, achieving 95.2% average success versus 40.95% for synchronous baselines on seven real-world manipulation tasks while enabling 100 Hz control.
-
vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
vla.cpp is a unified C++ runtime that serves multiple VLA architectures with flow-matching and diffusion patterns, matching SOTA performance on LIBERO while running on low-memory embedded hardware.
-
DEFLECT: Delay-Robust Execution via Flow-matching Likelihood-Estimated Counterfactual Tuning for VLA Policies
DEFLECT is an offline post-training method that improves async VLA policy success rates under high inference delays by using flow-matching likelihood ratios on counterfactual fresh/stale action pairs from a frozen reference policy.
-
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
ElegantVLA accelerates VLA models up to 3.77x by dynamically scheduling compute across vision, language, and action components without retraining the base model.
-
LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception
LiteVLA-H delivers 19.74 Hz action tokens and 6 Hz semantic outputs on Jetson Orin via dual-rate scheduling and mixed fine-tuning, outperforming recent VLA baselines in edge action rate while preserving descriptive competence.