Zobrazeno 1 - 10
of 2 293
pro vyhledávání: '"LIU Sijia"'
Autor:
Deng Dejun, Huang Yanghua, You Shufeng, Li Shengcai, Liu Yanmin, Chi Changjia, Huang Siqi, Liu Sijia
Publikováno v:
E3S Web of Conferences, Vol 490, p 02005 (2024)
Urban design rainstorm is the basis of urban hydraulic engineering design, which is related to the safety and economy of urban drainage engineering, and has an important impact on the design scale and investment of urban drainage engineering. Scienti
Externí odkaz:
https://doaj.org/article/a22701dae7c4497499b08c26115746a5
Autor:
Sun, Changchang, Wang, Ren, Zhang, Yihua, Jia, Jinghan, Liu, Jiancheng, Liu, Gaowen, Liu, Sijia, Yan, Yan
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations like the ``right to be forgotten
Externí odkaz:
http://arxiv.org/abs/2412.16780
Autor:
Zhuang, Haomin, Zhang, Yihua, Guo, Kehan, Jia, Jinghan, Liu, Gaowen, Liu, Sijia, Zhang, Xiangliang
Recent advancements in large language model (LLM) unlearning have shown remarkable success in removing unwanted data-model influences while preserving the model's utility for legitimate knowledge. However, despite these strides, sparse Mixture-of-Exp
Externí odkaz:
http://arxiv.org/abs/2411.18797
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious edits to human portraits that threaten privacy and identity security. E
Externí odkaz:
http://arxiv.org/abs/2411.16832
Autor:
Zhang, Yimeng, Zhi, Tiancheng, Liu, Jing, Sang, Shen, Jiang, Liming, Yan, Qing, Liu, Sijia, Luo, Linjie
The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it presents significant challenges for existing technologies. A persistent
Externí odkaz:
http://arxiv.org/abs/2411.13632
Autor:
Zhang, Ruichen, Yao, Yuguang, Tan, Zhen, Li, Zhiming, Wang, Pan, Liu, Huan, Hu, Jingtong, Liu, Sijia, Chen, Tianlong
Image generation is a prevailing technique for clinical data augmentation for advancing diagnostic accuracy and reducing healthcare disparities. Diffusion Model (DM) has become a leading method in generating synthetic medical images, but it suffers f
Externí odkaz:
http://arxiv.org/abs/2410.22551
The need for effective unlearning mechanisms in large language models (LLMs) is increasingly urgent, driven by the necessity to adhere to data regulations and foster ethical generative AI practices. Despite growing interest of LLM unlearning, much of
Externí odkaz:
http://arxiv.org/abs/2410.17509
In this work, we address the problem of large language model (LLM) unlearning, aiming to remove unwanted data influences and associated model capabilities (e.g., copyrighted data or harmful content generation) while preserving essential model utiliti
Externí odkaz:
http://arxiv.org/abs/2410.07163
Autor:
Ferraz, Thomas Palmeira, Mehta, Kartik, Lin, Yu-Hsiang, Chang, Haw-Shiuan, Oraby, Shereen, Liu, Sijia, Subramanian, Vivek, Chung, Tagyoung, Bansal, Mohit, Peng, Nanyun
Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post "in a funny tone" with "no hashtag"). Desp
Externí odkaz:
http://arxiv.org/abs/2410.06458
Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient diffusion
Externí odkaz:
http://arxiv.org/abs/2409.19128