14 citations · 26 across the 8 of their papers we have counts for
8 papers
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…
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…
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…
EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs
Xiangyu Zhao, Bo Liu, Qijiong Liu +2
We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLM…
Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning
Guangyuan Shi, Qimai Li, Wenlong Zhang +2
A fundamental challenge for multi-task learning is that different tasks may conflict with each other when they are solved jointly, and a cause of this phenomenon is conflicting gra…
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…
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…
Effectiveness of Pre-training for Few-shot Intent Classification
Haode Zhang, Yuwei Zhang, Li-Ming Zhan +4
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a…