DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models

Siyuan Xu; Tianshi Wang; Fengling Li; Lei Zhu; Heng Tao Shen

cs.ROApr 13, 2026

DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models

Authors: Siyuan Xu, Tianshi Wang, Fengling Li, Lei Zhu, Heng Tao Shen

Organizations: Tongji University Shanghai, China · University of Technology Sydney Sydney, Australia

Abstract

Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands. While Post-Training Quantization (PTQ) provides an efficient solution, directly applying PTQ to VLAs often results in severe performance degradation during sequential control. We identify temporal error accumulation as a key factor, where quantization perturbations at the vision-language-to-action interface are progressively amplified, leading to kinematic drift in executed trajectories. To address this issue, we propose Drift-Aware Post-Training Quantization (DA-PTQ), which formulates quantization as a drift-aware optimization problem over sequential decision processes. DA-PTQ consists of two components: (1) Cross-Space Representation Compensation, which mitigates structured distortions between multimodal representations and action space to improve action consistency, and (2) Motion-Driven Mixed-Precision Allocation, which assigns bit-widths by minimizing trajectory-level motion errors. Extensive experiments show that DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings, enabling practical deployment of VLAs on resource-limited robotic platforms.

Figures & tables

Figure 1. Comparison between previous PTQ strategies and our DA-PTQ. (a) Conventional uniform quantization distorts the conditioning interface, resulting in trajectory drift during sequential control. (b) DA-PTQ stabilizes execution through cross-space representation compensation and motion-driven mixed-precision allocation, thereby preserving kinematically sensitive components.

Figure 2. Overview of our proposed DA-PTQ framework. DA-PTQ enables efficient and robust diffusion-based VLA models through two key components: (1) Cross-Space Representation Compensation, which aligns distorted conditioning representations with their full-precision counterparts; and (2) Drift-Aware Mixed-Precision Allocation, which leverages structural Jacobian-based sensitivity to mitigate compounding trajectory drift.

Method	Sources	Success Rate ( $\uparrow$ )	Memory Reduction ( $\uparrow$ )	Speedup ( $\uparrow$ )
VLA-Cache	NeurIPS’25	46.8	0.0	36.7
QuantVLA	CVPR’26	43.5	42.7	55.8
Ours	—	48.9	42.5	54.8

Table 1. Efficiency-performance trade-off on SimplerEnv.

WidowX Robot	Methods	Sources	Tasks				Average Success Rate ( $\uparrow$ )
WidowX Robot	Methods	Sources	Put Spoon on Towel	Put Carrot on Plate	Stack Green Block on Yellow Block	Put Eggplant in Yellow Basket	Average Success Rate ( $\uparrow$ )
SIMPLER (Visual Matching)	CogACT (FP)	Arxiv’24	71.7	50.8	15.0	67.5	51.3
	VLA-Cache	NeurIPS’25	78.3	39.1	17.4	52.2	46.8
	QuantVLA	CVPR’26	47.8	39.1	17.4	69.6	43.5
	Ours	—	65.2	52.2	17.4	60.9	48.9

Table 2. In-domain performance on WidowX under the SimplerEnv Visual Matching setting.

Google Robot	Methods	Sources	Tasks				Average Success Rate ( $\uparrow$ )
Google Robot	Methods	Sources	Pick Coke Can	Move Near	Open/Close Drawer	Open Top Drawer and Place Apple	Average Success Rate ( $\uparrow$ )
SIMPLER (Visual Matching)	CogACT (FP)	Arxiv’24	91.3	85.0	71.8	50.9	74.8
	VLA-Cache	NeurIPS’25	92.0	83.3	70.5	51.6	74.4
	QuantVLA	CVPR’26	87.6	81.7	55.1	38.0	65.6
	Ours	—	92.4	87.9	58.3	35.2	68.5
SIMPLER (Variant Aggregation)	CogACT (FP)	Arxiv’24	89.6	80.8	28.3	46.6	61.3

Table 3. Cross-domain performance on Google Robot under SimplerEnv Visual Matching and Variant Aggregation settings.

Figure 3. Efficiency-performance trade-off across ablation variants on SimplerEnv.

WidowX Robot	Variants	Tasks				Average Success Rate ( $\uparrow$ )	Memory Reduction ( $\uparrow$ )	Speedup ( $\uparrow$ )
WidowX Robot	Variants	Put Spoon on Towel	Put Carrot on Plate	Stack Green Block on Yellow Block	Put Eggplant in Yellow Basket	Average Success Rate ( $\uparrow$ )	Memory Reduction ( $\uparrow$ )	Speedup ( $\uparrow$ )
SIMPLER (Visual Matching)	CogACT (FP)	71.7	50.8	15.0	67.5	—	—	—
	+ W4A8 + CSRC	66.7	41.7	12.5	54.2	43.8	42.6	55.2
	+ W4A8 + DA-MPA	50.0	45.8	12.5	50.0	39.6	42.9	54.8
	+ W4A8 + DA-PTQ	65.2	52.2	17.4	60.9	48.9	42.5	54.8

Table 4. Ablation study on WidowX under the SimplerEnv Visual Matching setting.

Figure 4. Task: Put Spoon on Towel (WidowX Robot). The top panel illustrates the seamless sequential execution by the DA-PTQ quantized model. The bottom panel displays the generated temporal action curves across 7 degrees of freedom, highlighting the absence of quantization-induced oscillations and the smoothness of the low-bit control signals.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Module	Parameter	Value
Calibration	Calibration Steps	$512$
	Batch Size	$1$
	Spatial Bins	$6$
	Warmup Steps	$128$
DA-MPA	Probe Steps	$16$
	Damping Factor ( $\lambda$ )	$3\times 10^{-4}$

Appendix

Table 5. Summary of core hyperparameters used in the DA-PTQ calibration pipeline.

Figure 5. Task: Put Eggplant in Yellow Basket (WidowX Robot). DA-PTQ maintains precise and dynamically stable motor commands throughout the episode, guiding the end-effector to successfully complete the manipulation without kinematic drift.

Figure 6. Task: Move Near (Google Robot). This qualitative result demonstrates the cross-embodiment generalizability of DA-PTQ. Even deployed on a completely different robotic kinematic structure, the 4-bit framework generates highly accurate and coherent continuous control commands.

Explore similar work

CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation
Oct 2, 2026Jin Hyun, Jung Gyu Min, Gyuhyun Jung +1Post-Training Quantization VLM Quantization
KAIST, Daejeon, South Korea · POSTECH, Pohang, South Korea
DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
Mar 9, 2026Zihao Zheng, Hangyu Cao, Chibang Tao +9VLM Quantization Efficient VLA Model Inference
School of Computer Science, Peking University, Beijing, China. · School of Software Engineering, South China University of Technology, Guangzhou, China. · School of Artificial Intelligence, Beijing Normal University, Beijing, China. +1
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
Feb 23, 2026Jingxuan Zhang, Yunta Hsieh, Zhongwei Wan +5Efficient VLA Model Inference Post-Training Quantization
The Ohio State University · University of Michigan · City University of Hong Kong

Oct 2, 2026J/K move · Enter open · S save

CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation

Jin Hyun, Jung Gyu Min, Gyuhyun Jung, Youngjoo Lee

KAIST, Daejeon, South Korea · POSTECH, Pohang, South Korea

Post-Training Quantization VLM Quantization Efficient VLA Model Inference Activation Quantization

Open paper AskPDF arXiv

Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (AE) poses a key challenge for low-bit post-training quantization (PTQ). The AE is repeatedly invoked across denoising steps and policy queries, where fixed calibration scales can be mismatched with activation ranges that vary with denoising progress and intended motion. We propose CHASE-VLA, a chunk-aware PTQ method that exploits a VLA-specific signal readily available from the policy: the generated action chunk, including its unexecuted future suffix. Rather than relying only on static scale matching for AE layers, CHASE-VLA combines the previously generated chunk as causal action context with denoising step group information to adapt AE activation scales. This enables W4A4 quantization of both MLP and attention projections in the repeated AE without modifying the pretrained policy. On LIBERO, CHASE-VLA achieves 97.3% average success rate on

π_{0.5}

when both MLP and attention projections in the AE are quantized to W4A4, restoring FP16-level performance. CHASE-VLA also reduces the weight storage of the quantized AE linear layers by 73.4% and their single-chunk memory traffic by 70.9% and 71.2% on

π_{0.5}

and GR00T N1.6, respectively, with a predictor overhead of at most 1.26% of the saved storage.

Abstract

Explore similar work

CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models