4 papers
GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
Yunan Zhang, Shuoran Jiang, Mengchen Zhao +4
The continual learning capability of large language models (LLMs) is crucial for advancing artificial general intelligence. However, continual fine-tuning LLMs across various domai…
Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning
Yukang Lin, Bingchen Zhong, Shuoran Jiang +2
Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite…
Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning
Shuoran Jiang, Qingcai Chen, Xin Liu +2
Graph convolutional network (GCN) has become popular in various natural language processing (NLP) tasks with its superiority in long-term and non-consecutive word interactions. How…
Text-Guided Neural Image Inpainting
Lisai Zhang, Qingcai Chen, Baotian Hu +1
Image inpainting task requires filling the corrupted image with contents coherent with the context. This research field has achieved promising progress by using neural image inpain…