Zobrazeno 1 - 10
of 100
pro vyhledávání: '"Zhu, Minfeng"'
Recent advancements in pre-trained Vision-Language Models (VLMs) have highlighted the significant potential of prompt tuning for adapting these models to a wide range of downstream tasks. However, existing prompt tuning methods typically map an image
Externí odkaz:
http://arxiv.org/abs/2408.09706
Autor:
Zhou, Jiehui, Wang, Xumeng, Wong, Kam-Kwai, Zhang, Wei, Liu, Xingyu, Zhang, Juntian, Zhu, Minfeng, Chen, Wei
In causal inference, estimating Heterogeneous Treatment Effects (HTEs) from observational data is critical for understanding how different subgroups respond to treatments, with broad applications such as precision medicine and targeted advertising. H
Externí odkaz:
http://arxiv.org/abs/2407.01893
Autor:
Zhang, Wei, Kam-Kwai, Wong, Xu, Biying, Ren, Yiwen, Li, Yuhuai, Zhu, Minfeng, Feng, Yingchaojie, Chen, Wei
The integration of new technology with cultural studies enhances our understanding of cultural heritage but often struggles to connect with diverse audiences. It is challenging to align personal interpretations with the intended meanings across diffe
Externí odkaz:
http://arxiv.org/abs/2405.00435
Autor:
Pan, Bo, Lu, Jiaying, Wang, Ke, Zheng, Li, Wen, Zhen, Feng, Yingchaojie, Zhu, Minfeng, Chen, Wei
The potential of automatic task-solving through Large Language Model (LLM)-based multi-agent collaboration has recently garnered widespread attention from both the research community and industry. While utilizing natural language to coordinate multip
Externí odkaz:
http://arxiv.org/abs/2404.11943
Autor:
Feng, Yingchaojie, Chen, Zhizhang, Kang, Zhining, Wang, Sijia, Zhu, Minfeng, Zhang, Wei, Chen, Wei
The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential misuse. A
Externí odkaz:
http://arxiv.org/abs/2404.08793
The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities. In this pap
Externí odkaz:
http://arxiv.org/abs/2402.13669
Autor:
Feng, Yingchaojie, Wang, Xingbo, Wong, Kam Kwai, Wang, Sijia, Lu, Yuhong, Zhu, Minfeng, Wang, Baicheng, Chen, Wei
Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. However, developing effective prompts for desired images can be challenging
Externí odkaz:
http://arxiv.org/abs/2307.09036
Autor:
Wen, Zhen, Liu, Yihan, Tan, Siwei, Chen, Jieyi, Zhu, Minfeng, Han, Dongming, Yin, Jianwei, Xu, Mingliang, Chen, Wei
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics, 2023
Quantum computing is a rapidly evolving field that enables exponential speed-up over classical algorithms. At the heart of this revolutionary technology are quantum circuits, which serve as vital tools for implementing, analyzing, and optimizing quan
Externí odkaz:
http://arxiv.org/abs/2307.08969
Autor:
Feng, Haozhe, Yang, Zhaorui, Chen, Hesun, Pang, Tianyu, Du, Chao, Zhu, Minfeng, Chen, Wei, Yan, Shuicheng
Without access to the source data, source-free domain adaptation (SFDA) transfers knowledge from a source-domain trained model to target domains. Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, b
Externí odkaz:
http://arxiv.org/abs/2304.06627
Autor:
Weng, Luoxuan, Zhu, Minfeng, Wong, Kam Kwai, Liu, Shi, Sun, Jiashun, Zhu, Hang, Han, Dongming, Chen, Wei
Large language models (LLMs) have gained popularity in various fields for their exceptional capability of generating human-like text. Their potential misuse has raised social concerns about plagiarism in academic contexts. However, effective artifici
Externí odkaz:
http://arxiv.org/abs/2304.05011