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 Concept Videos

Multicompartment Models: Overview01:14

Multicompartment Models: Overview

683
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
683
Reducing Line Loss01:18

Reducing Line Loss

430
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...
430
Hyperbolas01:30

Hyperbolas

514
A hyperbola is a conic section produced when a double-napped cone is intersected by a plane at an angle steeper than the slope of the cone, such that it cuts through both nappes. This intersection yields two separate, mirror-image curves known as branches, which open away from each other along the transverse axis. The nearest points on each branch to the hyperbola’s center are termed vertices, and the distance from the center to a vertex is denoted by a. Perpendicular to the transverse...
514
Upsampling01:22

Upsampling

682
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
682
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

517
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
517
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

383
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
383

You might also read

Related Articles

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

Sort by
Same author

Ionic Liquid-Laden Mesoporous Silica for Ultrafast Gold Recovery Via Nanoconfined Interfacial Anion Exchange.

The journal of physical chemistry letters·2026
Same author

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks.

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

Screening and enrichment of quercetin from Tetrastigma hemsleyanum Diels & Gilg toward targeted micellar delivery for lung cancer therapy.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Dual-Responsive Polymer Nanocarriers Loaded with Active Ingredients of <i>Tetrastigma Hemsleyanum</i> Diels et Gilg for Targeted Therapy of Lung Cancer.

Biomacromolecules·2026
Same author

Heterogeneous neural blind deconvolution: A signal processing-empowered foundation feature extractor for bearing fault diagnosis.

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

Quantifying the Contribution of Intrachain Conformational Locking to Covalent Hydrogel Mechanics.

Langmuir : the ACS journal of surfaces and colloids·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

Related Experiment Video

Updated: Mar 15, 2026

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K

Hyper-Compression: Model Compression via Hyperfunction.

Feng-Lei Fan, Juntong Fan, Dayang Wang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |March 13, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Hyper-compression offers a novel approach to large model compression by representing parameters through dynamic systems. This method achieves significant compression ratios with minimal performance loss, requiring no retraining and offering fast processing times.

    Related Experiment Videos

    Last Updated: Mar 15, 2026

    Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
    09:47

    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

    Published on: December 15, 2023

    2.0K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computational Science

    Background:

    • The exponential growth in large model size outpaces available computing resources.
    • Existing model compression techniques like pruning and quantization have limitations.

    Purpose of the Study:

    • To introduce a novel model compression technique called hyper-compression.
    • To address the gap between large model size and computing resource limitations.

    Main Methods:

    • Hyper-compression represents model parameters using dynamic systems as hyperfunctions.
    • A dynamic system with irrational winding is identified as the hyperfunction.
    • Theoretical error bounds are derived, and engineering optimizations are applied.

    Main Results:

    • Hyper-compression achieves preferable compression ratios without post-hoc retraining.
    • It offers affordable inference and short compression times, compressing LLaMA2-7B in one hour.
    • Performance degradation is less than 1%, comparable to int4-quantization.

    Conclusions:

    • Hyper-compression presents a distinct and effective mechanism for large model compression.
    • The method is pragmatic, efficient, and achieves high performance with significant size reduction.