Papers by Shaokang Zhang

2 papers
Dynamic Nonlinear Mixup with Distance-based Sample Selection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to augment data with mixup are limited by the space of synthetic data and its regularization effect.
Approach: They propose a dynamic nonlinear mixup with distance-based sample selection which generates multiple sample pairs based on the distance between each sample.
Outcome: The proposed method outperforms state-of-the-art methods on multiple public datasets.
TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies have shown that LoRA introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning.
Approach: They propose a method that leverages importance information from the pretrained model’s weights to mitigate LoRA redundancy.
Outcome: The proposed method significantly reduces the number of trainable parameters required for task adaptation while providing a task-aligned perspective for LoRA redundancy reduction.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations