PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

Hojin Jeon; Jimin Lee; Taekwan Kim; Nayoung Oh; Taeyoung Kim; Myungkyu Koo; Jinmo Koo; Joonwoo Ahn

cs.ROOct 19, 2026

PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

Authors: Hojin Jeon, Jimin Lee, Taekwan Kim, Nayoung Oh, Taeyoung Kim, Myungkyu Koo, Jinmo Koo, Joonwoo Ahn,

Organizations: KAIST · Korea University · RLWRLD · Seoul National University

Abstract

Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generalist robot policies, their execution often remains temporally inefficient. A key source of this inefficiency is that policies learn fine-grained temporal patterns from teleoperated demonstrations, requiring many low-level action steps. Temporal action quantization offers a simple way to accelerate execution by aggregating consecutive low-level actions into temporally coarser actions. However, applying action quantization without considering when fine-grained control is required introduces a speed-accuracy trade-off: accelerated actions may efficiently reduce redundant steps in some phases, while discarding critical motion details in precision-sensitive interactions. To address this, we propose PaceVLA, a unified framework for adaptive temporal execution in VLAs that integrates two coupled components: (1) mode-specific action decoders built on a shared action expert, supporting multiple temporal granularities and prediction horizons, and (2) a quantizability-guided mode selection scheme which decides whether coarse execution is appropriate, and a context-conditioned router that selects an execution mode at each inference step. Experiments across three multi-task simulation benchmarks and six real-world tasks show that PaceVLA improves execution efficiency while maintaining task success rate across multiple embodiments, including long-horizon and dexterous manipulation.

Figures & tables

Panel of Figure 1 — Figure 1: Adaptive temporal execution with PaceVLA . (a) Conveyor package handling task on the humanoid ALLEX: PaceVLA selects a temporal granularity per phase. (b) Success rate vs. speedup over the base VLA, averaged over six real-world tasks.

Figure 2: Overview of PaceVLA . PaceVLA is a unified framework for adaptive temporal action execution in pretrained VLAs. It equips a shared action expert with mode-specific action decoders that support different temporal granularities and prediction horizons.

Figure 3: Experimental setup. Top: Three simulation benchmarks, LIBERO, RoboCasa-Kitchen, and DexJoCo. Bottom: Real-world manipulation tasks across three embodiments, a Franka Research Arm with a gripper, an OpenArm robot with a dexterous hand, and an ALLEX humanoid. The real-world evaluation includes long-horizon and dexterous manipulation tasks.

Method	RoboCasa-Kitchen						LIBERO
	PnP			Others			Short			Long
	SR $\uparrow$	TPR $\uparrow$	ES $\uparrow$	SR $\uparrow$	TPR $\uparrow$	ES $\uparrow$	SR $\uparrow$	TPR $\uparrow$	ES $\uparrow$	SR $\uparrow$	TPR $\uparrow$	ES $\uparrow$
RLDX-1-IMG [ 18 ]	48.5	1.10	1.00	76.3	2.73	1.00	96.7	7.93	1.00	88.6	3.15	1.00
+ Fixed Quantization [ 30 ]	43.0	1.55	0.87	72.0	4.00	0.97	89.4	11.80	1.23	79.2	4.44	1.10
+ DemoSpeedUp [ 13 ]	28.7	0.80	0.49	62.7	3.37	0.68	93.5	14.03	1.54	75.2	4.95	1.06
+ SAIL [ 2 ]	38.5	1.03	0.72	66.6	2.80	0.75	96.5	10.34	1.27	76.6	3.38	0.92

Table 1: Simulation benchmark results. We compare PaceVLA with baseline methods on RoboCasa-Kitchen and LIBERO. For RoboCasa-Kitchen, we report results on the pick-and-place tasks (PnP) and the remaining tasks (Others), with models trained using 300 demonstrations per task. For LIBERO, we report results on the short-horizon suites (Short, averaged over Spatial, Object, and Goal) and the long-horizon suite (Long). We report the success rate (SR, %), throughput-with-regret (TPR,

\times 10^{-3}

), and the effective speedup (ES). Base models are listed for reference (

\mathrm{ES}=1

by definition). Among the acceleration methods for each base model, the best and second-best results are in bold and underlined , respectively.

	Franka + Gripper						OpenArm + Bimanual Hand
	Pick-and-Place		Air Fryer		Stack Cup		Table Sweeping		Pump and Scrub
Method	SR $\uparrow$	Time (s) $\downarrow$	SR $\uparrow$	Time (s) $\downarrow$	SR $\uparrow$	Time (s) $\downarrow$	SR $\uparrow$	Time (s) $\downarrow$	SR $\uparrow$	Time (s) $\downarrow$
GR00T N1.5 [ 5 ]	81.3	12.1	81.3	24.6	84.4	35.3	62.5	21.9	64.1	30.0
+ Fixed Quantization [ 30 ]	62.5	7.7	53.1	14.2	62.5	18.7	48.4	13.3	42.2	19.9
+ DemoSpeedUp [ 13 ]	68.8	8.1	71.9	18.9	53.1	24.2	56.3	17.9	53.1	20.2
+ SAIL [ 2 ]	65.6	7.9	56.3	16.8	45.3	20.0	46.9	15.4	45.3	15.3

Table 2: Real-World evaluation results. We report average success rate (SR, %, over 32 trials per task; partial scores of 0.5 are given on Stack Cup, Table Sweeping, and Pump and Scrub, see Appendix C ) and execution time (Time, average wall-clock execution time on fully successful trials) on five real-world tasks across two embodiments: three Franka+Gripper tasks ( Pick-and-Place, Air Fryer, Stack Cup ) and two OpenArm+Hand tasks ( Table Sweeping, Pump and Scrub ).

Table 6

Method SR

\uparrow

TPR

\uparrow

\uparrow

w/o Mode-specific Decoders 63.3 2.44 1.00 w/o Quantization Judge 65.1 2.01 1.01 PaceVLA 66.9 2.75 1.14

(a) Component ablation.

Table 5: Ablation study. Success rate (SR, %), throughput-with-regret (TPR,

\times 10^{-3}

), and effective speedup (ES) on RoboCasa-Kitchen, averaged over all 24 tasks. ES is computed relative to the base model GR00T N1.5. Our default setting is highlighted in violet .

Method	Latency (ms) $\downarrow$	Rel. Cost
GR00T N1.5	40.07	$1.00\times$
PaceVLA	42.15	$1.05\times$

Table 6: Inference cost. Per-step latency on RoboCasa-Kitchen.

Figure 4: Quantizability supervision analysis. We visualize the quantizability scores annotated on a RoboCasa-Kitchen demonstration. Shaded bands indicate manipulation phases. Scores are low around contact transitions (grasp and place) and higher during reach and carry, so coarse execution is suppressed exactly where precise control matters.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 5 — Figure 5: Hardware setups and task environments.

	GR00T N1.5 + PaceVLA	RLDX-1-IMG + PaceVLA
Optimizer	AdamW	AdamW
Optimizer momentum	$\beta_{1},\beta_{2}=0.95,0.999$	$\beta_{1},\beta_{2}=0.9,0.999$
Optimizer weight decay	1e-5	1e-5
Learning rate	1e-4	1e-4
Learning rate scheduler	Cosine decay	Cosine decay
Warmup iterations	3,000	3,000

Appendix

Table 7: Hyperparameter details for training PaceVLA on simulation benchmarks.

	Franka	OpenArm	ALLEX
Batch size	64	64	256
Training iterations	30,000	40,000	30,000
Fine-grained modes	$(16,16),\ (8,8)$	$(16,16),\ (8,8)$	$(24,24),\ (12,12)$
Quantized modes	$(16,8),\ (8,4)$	$(16,8),\ (8,4)$	$(24,12),\ (12,6)$

Appendix

Table 9: Embodiment-specific settings for real-world tasks. Modes are given as

(H_{k},T_{k})

Decoder $(H,q)$	Metric	Ours	Base
(16,2)	MSE $\downarrow$	0.0273	0.0344
	DTW $\downarrow$	3.209	3.777
	Cosine $\uparrow$	0.850	0.809
(8,2)	MSE $\downarrow$	0.0163	0.0243
	DTW $\downarrow$	1.359	1.658
	Cosine $\uparrow$	0.886	0.847

Appendix

Table 10: Quantized-action prediction accuracy on RoboCasa-Kitchen. Ours uses dedicated coarse decoders, while Base quantizes GR00T N1.5 predictions using the same SO(3)-aware rule.

(H,q)

denotes the source horizon and quantization level, and Both averages the two configurations.

Figure 6: End-effector rollout trajectories. End-effector trajectories of the base policy (blue) and PaceVLA (orange) from the same initial state; PaceVLA traverses the same path with fewer, sparser steps.

Figure 7: Failure cases of PaceVLA . Most failures come from small targeting errors (Pick-and-Place, Stack Cup) or from the hands and tools blocking the contact region in the egocentric view (Table Sweeping, Pump and Scrub).

Efficient VLA Model Inference

Efficient vision-language-action (VLA) model inference reduces robot-control latency, memory use, and energy while preserving task performance.

See all 190 papers

TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
Jun 4, 2026Dong Jing, Jingchen Nie, Tianqi Zhang +4Robotic Control Vision-Language-Action Models
1RUC · 2FDU · 3UNC
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
May 28, 2026Ye Li, Huanan Liu, Kangye Ji +7Efficient VLM Inference Efficient VLA Model Inference
Tsinghua University · University of Illinois at Urbana-Champaign
Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference
Jul 14, 2026Yuzhou Wu, Yuxin Zheng, Muchun Niu +6Efficient VLA Model Inference Efficient VLA Models
1Tianji KernalMind co ltd · 2Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · 3Shanghai Jiao Tong University, Shanghai, China +2

Jun 4, 2026J/K move · Enter open · S save

TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies

Dong Jing, Jingchen Nie, Tianqi Zhang, Jiaqi Liu+3

1RUC · 2FDU · 3UNC

Robotic Control Vision-Language-Action Models Robot Learning

Open paper AskPDF arXiv

Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Language-Action models (VLAs) only inherit a single fixed speed from training demonstrations. Prior efforts to accelerate VLAs through model compression, KV-cache reuse, or reinforcement learning only shift the policy from one fixed speed to another, and leave deceleration almost unexplored. We observe that the magnitude of each predicted action already governs how fast the robot moves, opening a direct route to controllable execution speed. We turn this observation into TempoVLA, a single VLA whose execution speed is controlled by an explicit condition. TempoVLA combines two coupled components. (1) A data-side Variable-Speed Trajectory Augmentation (VSTA) that re-times demonstration to any target speed by merging or splitting actions while preserving its motion semantics. (2) A model-side conditioning mechanism that feeds the speed to the policy. Statistics show that VSTA reaches the requested speed with negligible motion error. Experiments in simulation and on real-world tasks demonstrate that TempoVLA achieves flexible speed control in both directions, while VSTA additionally boosts the default

1\times

performance via better data utilization. Furthermore, by cooperating with a large multimodal model, TempoVLA realizes dynamic speed control, accelerating through low-risk phases and decelerating for high-risk ones.

Abstract

Efficient VLA Model Inference

Explore similar work

TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models

Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference