VLM Quantization

VLM: Vision-Language Model

Vision-language model quantization studies how to represent model weights, activations, and key-value caches with fewer bits so models can run with less memory and compute. Post-training quantization typically uses calibration data and sensitivity measures, while quantization-aware training and distillation adapt models during training; common techniques include mixed precision, modality-aware scaling, rotations, and token or cache selection. Work evaluates these methods on visual question answering, image understanding, and increasingly embodied tasks, with deployment studies measuring latency, memory, and energy on target hardware. A central tension is that strong average accuracy or memory savings do not guarantee reliable grounding, uncertainty estimates, or faster real-world inference, especially at very low bit widths.

Latest papers

53 papers10 papers in the last four weeks, up 25% on the four weeks before. 0.1% of all new papers.

Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models
Oct 28, 2026Jiuyi Xu, Xiao Hu, Meida Chen +3Mixed-Precision Quantization VLM Quantization
Colorado School of Mines · Northeastern University · USC Institute for Creative Technologies +1
AGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models
Oct 21, 2026Xuhong Qiu, Zhuoyu Wu, Qiawei Zheng +3VLM Quantization Efficient VLA Model Inference
School of Computer Science and Engineering, Southeast University, Nanjing, China · School of Information Technology, Monash University, Subang Jaya, Malaysia · Department of Electronic & Computer Engineering, Hong Kong University of Science & Technology, Hong Kong, China +1
Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning
Oct 11, 2026Seongmin Park, Jaewon Lee, Yujun Heo +4VLM Quantization Efficient VLA Model Inference
Hanyang University, Republic of Korea · LG Electronics, Republic of Korea
ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference
Oct 6, 2026Zou Qingyun, Bin Gao, Wenju Zhao +3Energy-Efficient ML VLM Quantization
National University of Singapore · Huazhong University of Science and Technology
Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
Oct 5, 2026Shen Ruan, Wenchang Gao, Jin Wang +4Vision-Language-Action Models OOD Generalization
Soochow University · Independent Researcher · Shanghai Jiao Tong University +2
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
Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models
Sep 29, 2026Wenxiao Fan, Jingling Fu, Lichen Ma +6LLM Quantization VLM Quantization
School of Computer Science and Technology, Beijing Institute of Technology · Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model
Sep 28, 2026Rithvik Jonna, Man Namgung, Aakash Gurram +1Visual Navigation VLM Quantization
Department of Electrical and Computer Engineering Johns Hopkins University · Laboratory for Computational Sensing and Robotics Johns Hopkins University
SubRot: Signed Gradient Subspace Calibration for VLM Rotation Quantization
Sep 28, 2026Zhenhao Shang, Haizhao Jing, Haokui Zhang +4VLM Quantization Rotation-Based Quantization
Northwest Polytechnical University · Nanjing University of Science and Technology · Intellifusion +1
P4Q: Co-designing Token Pruning and Quantization for Vision-Language Model Acceleration
Sep 28, 2026Haizhao Jing, Zhenhao Shang, Haokui Zhang +2VLM Quantization Efficient VLM Inference
Northwest Polytechnical University · Intellifusion
Beyond Reconstruction Loss in Post-Training Quantization: Balanced Fitting for Large Vision-Language Models
Sep 28, 2026Minchan Kang, Kyeonghye Park, Seungyeon Sa +3VLM Quantization Large Vision-Language Models
Korea Advanced Institute of Science and Technology (KAIST) · Hanbat National University
GHOST-Q: Towards Studying Grounding Hallucinations Overlooked Under Same-score TradeOffs in Quantized VLMS
Sep 24, 2026Saim Rehman, Muhammad ShafiqueVLM Evaluation VLM Quantization
eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, UAE
RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
Sep 21, 2026Zhiping Wu, Dongdong Ren, Yangchengyu Zhou +4VLM Quantization Large Vision-Language Models
State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou 215163, China
SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models
Sep 21, 2026Kewei Zhang, Zheng Chen, Haotong Qin +1VLM Quantization Efficient VLM Inference
Shanghai Jiao Tong University · The Hong Kong Polytechnic University
FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding
Sep 21, 2026Hung T. Ho, Khanh D. Nguyen, Quang D. Nguyen +5VLM Quantization Efficient VLA Model Inference
VinRobotics, Vietnam · AICV Lab, EECS Department, University of Arkansas · School of Advanced Manufacturing and Robotics, Peking University, China +2
HeadGuard: Selective Head Protection for Low-Bit VLM KV-Cache Quantization
Sep 18, 2026Nenad BanficVLM Quantization KV-Cache Quantization
CoreAI, Microsoft
MiX: Micro-Inverted-Scaling for End-to-End Low-Bit Vision-Language Model Acceleration
Sep 17, 2026Yuan Liao, Jae-sun SeoAI Accelerator Inference VLM Quantization
Cornell Tech, Cornell University New York, NY, USA
Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models
Sep 15, 2026Jinwoo Jeon, GyuYeop Do, Yubin Lim +4VLM Quantization Efficient VLM Inference
Korea University · Seoul National University
BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering
Sep 7, 2026Sourajit Saha, Shubhashis Roy Dipta, Shaswati Saha +2VLM Quantization VLM Evaluation
University of Maryland, Baltimore County
Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs
Aug 21, 2026Luka Ribar, Jeevan Bhoot, Douglas OrrVLM Quantization Efficient VLM Inference
Graphcore Research · Arm
Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models
Aug 21, 2026Deepanshu Pandey, Arnav Chavan, Nahush Lele +2Quantization Robustness Neural Network Quantization
Amazon
Bigger or Cheaper? Scale and Quantization Effects on Uncertainty Signals in Vision-Language Models Under Image Degradation
Jul 27, 2026M M Asif FerdousVLM Robustness Selective Prediction
Independent Researcher
C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs
Jul 23, 2026Jiameng Li, Han Zhou, Matthew B. BlaschkoVLM Quantization Post-Training Quantization
1KU Leuven · 2Tiangong University
Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence
Jul 23, 2026Jay Gor, Karm Dave, Akshita Abrol +3Efficient Multimodal Inference VLM Quantization
Nirma University · Singapore Institute of Technology, Singapore · Department of CE-AI and Big Data, Marwadi University
StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design
Jul 20, 2026Yin Wang, Haotian Hu, Jineng Han +4Vision-Language Models VLM Quantization
StepX Team
Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment
Jul 9, 2026Hyeju Shin, Chorwon Kim, Ryangsoo Kim +2Mixed-Precision Quantization Vision-Language Models
1ETRI, Republic of Korea.
SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models
Jul 2, 2026Qi Lyu, Jiahua Dong, Baichen Liu +7Model Compression Vision-Language Models
State Key Laboratory of Robotics and Intelligent Systems · Shenyang Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences +2
Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
Jun 17, 2026Navin Ranjan, Andreas SavakisMixed-Precision Quantization VLM Quantization
Rochester Institute of Technology Rochester, New York 14623, USA
MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
Jun 15, 2026Yuanteng Chen, Peisong Wang, Zhilei Liu +9Mixed-Precision Quantization LLM Quantization
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · 3Zhongguancun Academy
Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling
May 27, 2026Xinyu Wang, Mingze Li, Sicheng Lyu +6Post-Training Quantization Efficient VLA Model Inference
McGill University · Université de Montréal · Mila – Quebec AI Institute +2

Oct 28, 2026J/K move · Enter open · S save

Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models

Jiuyi Xu, Xiao Hu, Meida Chen, Song Wang+2

Colorado School of Mines · Northeastern University · USC Institute for Creative Technologies+1

Mixed-Precision Quantization VLM Quantization Post-Training Quantization Efficient VLA Models Activation Quantization

Open paper AskPDF arXiv

Post-training quantization (PTQ) reduces the memory footprint of vision-language-action (VLA) models, but lowering bit widths while maintaining task performance remains challenging. Existing work has used sensitivity estimates from calibration data to assign bit widths to different model components. However, using task success directly to guide mixed-precision allocation is underexplored because closed-loop evaluations are costly and the effect of quantizing one component depends on the precision of other components. To this end, we propose QbD-VLA, a task-guided mixed-precision quantization method that uses task success from short closed-loop evaluations to assign weight and activation bit widths while accounting for interactions between model components. Experiments covering four VLA models and all four LIBERO suites show strong task performance at average precisions of approximately 4 bits for weights and fewer than 6 bits for activations. On SIMPLER, the gain over uniform quantization is small. On a Franka Research 3 robot arm, simulation-selected allocations show no detected success-rate loss on X-VLA but fail on

π_{0.5}

. These findings support using task success to guide mixed-precision VLA quantization, while highlighting the need for real-world evaluation before deployment. Code is available at github.com/jiuyixu25/QbD-VLA.