works on

From the 1 of 56 linked papers with an AI index.

activity
20242026
most citedT-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems

1 citations · 1 across the 23 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning

Yongkang Liu, Zijing Wang, Mengjie Zhao +7

This work presents \textsc{ChunkFT}, a memory-efficient fine-tuning framework that reformulates full-parameter fine-tuning around a dynamically activated working set. \textsc{Chunk…

cs.LG2026

SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning

Yongkang Liu, Xing Li, Mengjie Zhao +7

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation…

cs.LG2026

MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis

Xingle Xu, Yongkang Liu, Dexian Cai +4

Multimodal Sentiment Analysis aims to integrate information from various modalities, such as audio, visual, and text, to make complementary predictions. However, it often struggles…

cs.LG2025

Why Do More Experts Fail? A Theoretical Analysis of Model Merging

Zijing Wang, Xingle Xu, Yongkang Liu +6

Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. Although recent model merging methods hav…

cs.LG2025

Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning

Yongkang Liu, Xingle Xu, Ercong Nie +5

Parameter-Efficient Fine-Tuning (PEFT) methods achieve performance comparable to Full Fine-Tuning (FFT) while requiring significantly fewer computing resources, making it the go-to…