Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 7, 2026

Mapping Molecular Diffusion in the Plasma Membrane by Multiple-Target Tracing (MTT)
12:19

Mapping Molecular Diffusion in the Plasma Membrane by Multiple-Target Tracing (MTT)

Published on: May 27, 2012

MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models With Temporal Distillation.

Weilun Feng, Chuanguang Yang, Haotong Qin

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |June 5, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    ¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)01:20

    ¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)

    When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Investigation of bioimpedance as a method for wearable noninvasive bladder volume measurements in individuals with spinal cord injury or disease: protocol of a feasibility study.

    Frontiers in urology·2026
    Same author

    Exponential synchronization of T-S fuzzy complex-valued BAM neural networks with mixed time-varying delays via event-triggered control engineering and applications.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    Real-time sparse signal reconstruction via KKT-conditions-driven analog circuit solver.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    Stability Switching and Oscillation Regulation Strategies for Large-Scale Fractional-Order Neural Networks With Double Hubs and Multiple Delays.

    IEEE transactions on cybernetics·2026
    Same author

    QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    Resilient State and Input Estimation for Complex Network Subject to Cyber Attack: A Set-Membership Method.

    IEEE transactions on cybernetics·2026
    Same journal

    Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Learning Shape Anchors for Holistic Indoor Scene Understanding.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    This study introduces MPQ-DMv2, a novel framework for extremely low-bit quantization of diffusion models. It significantly improves performance on edge devices by addressing limitations in existing quantization methods.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Diffusion models excel at vision generation but face computational challenges on edge devices.
    • Quantization accelerates inference and reduces memory but struggles with extremely low bit-widths (2-4 bits).
    • Existing quantization methods degrade performance due to outlier-unfriendly designs, suboptimal initialization, and optimization strategies.

    Purpose of the Study:

    • To develop an improved Mixed Precision Quantization (MPQ) framework for extremely low-bit diffusion models (MPQ-DMv2).
    • To enhance quantization techniques to handle outliers and imbalanced distributions effectively.
    • To optimize the training process for better convergence and temporal consistency in quantized models.

    Main Methods:

    Related Experiment Videos

    Last Updated: Jun 7, 2026

    Mapping Molecular Diffusion in the Plasma Membrane by Multiple-Target Tracing (MTT)
    12:19

    Mapping Molecular Diffusion in the Plasma Membrane by Multiple-Target Tracing (MTT)

    Published on: May 27, 2012

  • Proposed Flexible Z-Order Residual Mixed Quantization to manage salient errors from outliers using a binary residual branch.
  • Introduced Object-Oriented Low-Rank Initialization, analyzing LoRA module convergence for informative initialization.
  • Developed Memory-based Temporal Relation Distillation to maintain temporal consistency via an online pixel queue.

    • Main Results:

    • MPQ-DMv2 demonstrates superior performance compared to state-of-the-art methods across various generation tasks.
    • Significant improvements are observed especially under extremely low-bit width conditions (2-4 bits).
    • The framework shows effectiveness across different model architectures.

    Conclusions:

    • MPQ-DMv2 effectively overcomes the limitations of existing quantization methods for diffusion models at extremely low bit-widths.
    • The proposed techniques enable efficient and high-performance diffusion model deployment on resource-constrained edge devices.
    • This work paves the way for wider adoption of diffusion models in edge AI applications.