Xianjun Yang
Tsinghua University
24 Papers
1 Citations
Xianjun Yang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Convection. The author has an hindex of 2, co-authored 2 publications.
Chat about Author
Papers
LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation
TL;DR: The authors proposed LLMScore, a new framework that offers evaluation scores with multi-granularity compositionality, which leverages the large language models (LLMs) to evaluate text-to-image models.
29
A Survey on Detection of LLMs-Generated Content
Xianjun Yang,Liangming Pan,Xuandong Zhao,Haifeng Chen,L. Petzold,William Yang Wang,Wei Cheng +6 more
TL;DR: This work aims to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and identifying key challenges and prospects in the field, advocating for more adaptable and robust models to enhance detection accuracy.
28
On explosive boiling of a multicomponent Leidenfrost drop.
TL;DR: In this paper, the authors studied a unique explosive gasification process of a tricomponent droplet consisting of water, ethanol, and oil, by high-speed monitoring of the entire gasification event taking place in the well-controlled, levitated Leidenfrost state over a superheated plate.
26
Large Language Models Can Be Good Privacy Protection Learners
Yijia Xiao,Yiqiao Jin,Yushi Bai,Yue Wu,Xianjun Yang,Xiao Luo,Wenchao Xu,Xujiang Zhao,Yanchi Liu,Haifeng Chen,Wei Wang,Wei Cheng +11 more
TL;DR: Privacy Protection Language Models (PPLM) is introduced, a novel paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding data privacy and underscores the potential for Large Language Models as robust privacy protection learners.
OASum: Large-Scale Open Domain Aspect-based Summarization
TL;DR: Wang et al. as mentioned in this paper created a large-scale open-domain aspect-based summarization dataset named OASum, which contains more than 3.7 million instances with around 1 million different aspects on 2 million Wikipedia pages.