About

Hi👋, welcome to visit my academic website! I am a Ph.D. candidate at Institute of Computing Technology(ICT), Chinese Academy of Sciences(CAS), majoring in Computer Science and Technology. I work on Large Language Model Reasoning and Graph Data Mining.


Interests
  • Large Language Model
  • Graph Data Mining
Education
  • Ph.D Candidate, 2024-202X

    Institute of Computing Technology

  • B.S. in Computer Science, 2020-2024

    North China University of Technology

Publications

(2024). Translating Words to Worlds: Zero-Shot Synthesis of 3D Terrain from Textual Descriptions Using Large Language Models. Multimedia Tools and Applications (SCI Q1).

PDF Cite DOI

(2024). Frequency-Importance Gaussian Splatting for Real-Time Lightweight Radiance Field Rendering. Multimedia Tools and Applications (SCI Q2, CCF-C).

PDF Cite DOI

(2023). Attack based on data : A novel perspective to attack sensitive points directly. Cybersecurity (CCF-C).

PDF Cite Dataset DOI

Experience

 
 
 
 
 
Research Institute of Tsinghua University in Shenzhen
Machine Learning Engineer Intern
September 2023 – February 2024 Beijing, China
 
 
 
 
 
Microsoft Software Technology Center (STC) Asia
Software Engineer Intern
May 2023 – August 2023 Beijing, China
 
 
 
 
 
PaddlePaddle, Baidu
Software Engineer Intern
July 2021 – December 2021 Beijing, China

Recent Posts

EMNLP2024论文分享 | Fewer is More:CoT示例要少而精
作者提出CoT-Influx方法,一种对CoT的示例和内容进行优化从而提高LLMs推理能力的方法,其核心思想是通过剪枝最大化有效信息的输入。
论文分享 | 广泛的解码策略导致大模型越狱
在本文,作者提出了一个新的数据集MaliciousInstruct,一种模型回答毒性评估方式,一种通过操纵解码超参数的攻击手段——generation exploitation,一种对齐策略——generation-aware alignment
论文解读 | TTA:大模型回答置信度评估新方法
本文提出了一种新的方法,全面评估大模型多个候选答案的可信度,以减轻大模型对于错误答案的过度自信。
Softmax回归及其优化问题
本文所属系列为笔者学习陈天奇和J.Zico Kolter在CMU开设的Deep Learning Systems的课程笔记。
UCAS UCAS Long ICT