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

Survival Tree01:19

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a survival tree begins...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

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...
Linearization and Approximation01:26

Linearization and Approximation

Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...

You might also read

Related Articles

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

Sort by
Same author

Bound states in the continuum in plasmonic structures.

Reports on progress in physics. Physical Society (Great Britain)·2026
Same author

Coordination-driven self-assembly of antioxidative and anti-inflammatory cerium-luteolin nanoparticles for effective treatment of ocular alkali burns.

Journal of materials chemistry. B·2026
Same author

Sagittaria sagittifolia polysaccharide extract attenuates inflammation and senescence through dual involvement of TLR4/NF-κB and SIRT1/NF-κB in vivo and in vitro models of COPD.

Free radical biology & medicine·2026
Same author

Development and Internal Validation of a Nomogram Model to Predict Invasive Pulmonary Aspergillosis Occurrence Risk in ICU Patients with Sepsis.

Infection and drug resistance·2026
Same author

Construction of a classification model for liver fibrosis in MAFLD based on multiparametric MRI radiomics and machine learning: A rat study.

Medical physics·2026
Same author

Centimeter-Scale Two-Phase Mixed Re<sub>0.58</sub>Mo<sub>0.42</sub>S<sub>2</sub> Grown via Low-Pressure Chemical Vapor Deposition and Its Heterostructure with GaSe for High-Performance Photodetectors.

ACS applied materials & interfaces·2026
Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026
Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026
Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026
Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: Jun 24, 2026

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

Triangular Adaptive Low-Rank Adaptation for Parameter-Efficient Fine-Tuning.

Yao Liang, Yuwei Wang, Yi Zeng

    IEEE Transactions on Neural Networks and Learning Systems
    |June 22, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Triangular adaptive LoRA (TriAdapt-LoRA) enhances parameter-efficient fine-tuning (PEFT) for large language models (LLMs). This method improves flexibility and efficiency by adaptively allocating rank budgets to important modules.

    Related Experiment Videos

    Last Updated: Jun 24, 2026

    Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
    06:45

    Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

    Published on: October 28, 2022

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Natural Language Processing

    Background:

    • Parameter efficiency and adaptability are critical challenges in fine-tuning large language models (LLMs).
    • Existing parameter-efficient fine-tuning (PEFT) methods like low-rank adaptation (LoRA) have limitations in flexibility due to fixed low-rank adapters.
    • Underutilization of the low-rank structure in current PEFT approaches hinders optimal performance.

    Purpose of the Study:

    • To introduce TriAdapt-LoRA, a novel PEFT method designed for enhanced parameter efficiency and adaptability in LLMs.
    • To address the limitations of fixed low-rank adapters by incorporating a dynamic rank-growth scheme.
    • To develop a resource-efficient and scalable solution for fine-tuning LLMs.

    Main Methods:

    • Proposed TriAdapt-LoRA, featuring a triangular split-based low-rank parameterization for greater flexibility within the low-rank subspace.
    • Implemented a lightweight importance estimator using Frobenius norm changes of transformation matrices as a gradient-informed proxy for module contribution.
    • Introduced a dynamic-rank-growth mechanism to allocate a fixed global rank budget to the most critical modules during optimization.

    Main Results:

    • TriAdapt-LoRA demonstrated competitive performance against established PEFT baselines across diverse benchmarks, including natural language understanding, question answering, multimodal reasoning, and multilingual tasks.
    • The method often outperformed existing adaptive PEFT techniques like AdaLoRA and IncreLoRA under matched or reduced adaptation budgets.
    • Significantly reduced the computational cost associated with importance estimation, enhancing scalability and resource efficiency.

    Conclusions:

    • TriAdapt-LoRA offers a scalable and resource-efficient approach to fine-tuning LLMs, improving upon existing PEFT methods.
    • The adaptive rank-growth strategy effectively allocates limited adaptation capacity to the most impactful components.
    • This novel method provides a practical, fully gradient-based algorithm for advancing LLM fine-tuning capabilities.