activity
20212025
most citedOvercoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

14 citations · 14 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG2025

Recurrent Knowledge Identification and Fusion for Language Model Continual Learning

Yujie Feng, Xujia Wang, Zexin Lu +7

Continual learning (CL) is crucial for deploying large language models (LLMs) in dynamic real-world environments without costly retraining. While recent model ensemble and model me…

cs.CL2024

Understanding Layer Significance in LLM Alignment

Guangyuan Shi, Zexin Lu, Xiaoyu Dong +4

Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjus…

cs.CL2024

TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation

Yujie Feng, Xu Chu, Yongxin Xu +3

A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continu…

eess.IV2022

A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds

Wenlong Zhang, Guangyuan Shi, Yihao Liu +2

Degradation models play an important role in Blind super-resolution (SR). The classical degradation model, which mainly involves blur degradation, is too simple to simulate real-wo…

cs.LG202114 cited

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

Guangyuan Shi, Jiaxin Chen, Wenlong Zhang +2

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing…