Zobrazeno 1 - 10
of 36 177
pro vyhledávání: '"Lijie An"'
Autor:
Chi-Ming Liu, ZiChen Shao, XuZhou Chen, HanWu Chen, MengQiao Su, ZiWen Zhang, ZhengPing Wu, Peng Zhang, LiJie An, YinJie Jiang, Ai-Jun Ouyang
Publikováno v:
Saudi Pharmaceutical Journal, Vol 31, Iss 7, Pp 1219-1228 (2023)
Benign prostatic hyperplasia (BPH) is a common urinary disease among the elderly, characterized by abnormal prostatic cell proliferation. Neferine is a dibenzyl isoquinoline alkaloid extracted from Nelumbo nucifera and has antioxidant, anti-inflammat
Externí odkaz:
https://doaj.org/article/d6a77d813781480d844af31e551010b8
Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the formal guarantees of differential privacy (DP) in the embedding space. How
Externí odkaz:
http://arxiv.org/abs/2410.08027
Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is unclear. In th
Externí odkaz:
http://arxiv.org/abs/2410.06606
Currently, attention mechanisms have garnered increasing attention in Graph Neural Networks (GNNs), such as Graph Attention Networks (GATs) and Graph Transformers (GTs). It is not only due to the commendable boost in performance they offer but also i
Externí odkaz:
http://arxiv.org/abs/2410.06950
The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with multi-hop factual recall task
Externí odkaz:
http://arxiv.org/abs/2410.06331
Autor:
Lai, Songning, Yang, Jiayu, Huang, Yu, Hu, Lijie, Xue, Tianlang, Hu, Zhangyi, Li, Jiaxu, Liao, Haicheng, Yue, Yutao
Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs) have emerg
Externí odkaz:
http://arxiv.org/abs/2410.04823
We develop a Machine Learning Inversion method for analyzing scattering functions of mechanically driven polymers and extracting the corresponding feature parameters, which include energy parameters and conformation variables. The polymer is modeled
Externí odkaz:
http://arxiv.org/abs/2410.05574
Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer architectur
Externí odkaz:
http://arxiv.org/abs/2410.05076
Autor:
Liu, Aiwei, Bai, Haoping, Lu, Zhiyun, Sun, Yanchao, Kong, Xiang, Wang, Simon, Shan, Jiulong, Jose, Albin Madappally, Liu, Xiaojiang, Wen, Lijie, Yu, Philip S., Cao, Meng
Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is treated as a sin
Externí odkaz:
http://arxiv.org/abs/2410.04350
Autor:
Hu, Lijie, Liu, Liang, Yang, Shu, Chen, Xin, Tan, Zhen, Ali, Muhammad Asif, Li, Mengdi, Wang, Di
Large Language Models have demonstrated remarkable abilities across various tasks, with Chain-of-Thought (CoT) prompting emerging as a key technique to enhance reasoning capabilities. However, existing research primarily focuses on improving performa
Externí odkaz:
http://arxiv.org/abs/2410.03595