Picture for Shiyuan He

Shiyuan He

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

Add code
Oct 17, 2024
Figure 1 for LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning
Figure 2 for LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning
Figure 3 for LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning
Figure 4 for LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning
Viaarxiv icon

SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values

Add code
Sep 09, 2024
Figure 1 for SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
Figure 2 for SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
Figure 3 for SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
Figure 4 for SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
Viaarxiv icon

A Unified Analysis of Multi-task Functional Linear Regression Models with Manifold Constraint and Composite Quadratic Penalty

Add code
Nov 09, 2022
Viaarxiv icon