Zobrazeno 1 - 10
of 376
pro vyhledávání: '"Liu Zheyuan"'
Autor:
Yang, Tianyu, Dai, Lisen, Liu, Zheyuan, Wang, Xiangqi, Jiang, Meng, Tian, Yapeng, Zhang, Xiangliang
Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process. While progress has been made in unimodal domains like text and image classification, unlearni
Externí odkaz:
http://arxiv.org/abs/2410.23330
Autor:
Liu, Zheyuan, Dou, Guangyao, Jia, Mengzhao, Tan, Zhaoxuan, Zeng, Qingkai, Yuan, Yongle, Jiang, Meng
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns. While many pre
Externí odkaz:
http://arxiv.org/abs/2410.22108
Exploiting the foundation models (e.g., CLIP) to build a versatile keypoint detector has gained increasing attention. Most existing models accept either the text prompt (e.g., ``the nose of a cat''), or the visual prompt (e.g., support image with key
Externí odkaz:
http://arxiv.org/abs/2409.19899
Publikováno v:
Phys. Rev. Lett. 133, 156702 (2024)
Altermagnetism is a newly discovered magnetic class named after the alternating spin polarizations in both real and reciprocal spaces. Like the spin-splitting of electronic bands, the magnon bands in altermagnets are predicted to exhibit alternating
Externí odkaz:
http://arxiv.org/abs/2408.16490
Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning abilities. Howeve
Externí odkaz:
http://arxiv.org/abs/2407.20516
Autor:
Yang, Yiwei, Liu, Zheyuan, Jia, Jun, Gao, Zhongpai, Li, Yunhao, Sun, Wei, Liu, Xiaohong, Zhai, Guangtao
Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities. Coverless image steganography (CIS) enhances imperceptibility by not using any cover image. Recent works have utili
Externí odkaz:
http://arxiv.org/abs/2407.10459
Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world scenarios, model owners need to c
Externí odkaz:
http://arxiv.org/abs/2406.10952
Personalized large language models (LLMs) aim to tailor interactions, content, and recommendations to individual user preferences. While parameter-efficient fine-tuning (PEFT) methods excel in performance and generalization, they are costly and limit
Externí odkaz:
http://arxiv.org/abs/2406.10471
Autor:
Liang, Zhiding, Liu, Gang, Liu, Zheyuan, Cheng, Jinglei, Hao, Tianyi, Liu, Kecheng, Ren, Hang, Song, Zhixin, Liu, Ji, Ye, Fanny, Shi, Yiyu
In recent years, quantum computing has emerged as a transformative force in the field of combinatorial optimization, offering novel approaches to tackling complex problems that have long challenged classical computational methods. Among these, the Qu
Externí odkaz:
http://arxiv.org/abs/2403.03310
Graph plays an important role in representing complex relationships in real-world applications such as social networks, biological data and citation networks. In recent years, Large Language Models (LLMs) have achieved tremendous success in various d
Externí odkaz:
http://arxiv.org/abs/2402.10359