Xinyuan Wang

3869 Miramar st. Box 1214

La Jolla, California, USA, 92092

I am now an MSCS student at University of California, San Diego (UCSD), expected to graduate in Jun. 2024. And I plan to pursue a Ph.D. in the future. I am luckily to be mentored by professors at UCSD in both Natural Language Processing and Computer Vision, and have hands-on experiences in both fields. I am now mentored by Prof. Zhiting Hu and Postdoc. Zhen Wang in Large Language Model (LLM) Reasoning, Agent, and Prompting. I am also mentored by Prof. Zhuowen Tu in generative models (diffusion model). Before UCSD, I graduated from Central South University (CSU) in Hunan, China, mentored by Prof. Ying Zhao.

Research Interests

Large Language Models (LLMs) with World Models: Augmenting LLMs with a world model formulation to enable principled decision-making, planning, and simulation. Enhancing the LLM’s abilities in reasoning, planning, and interacting with the world. (LLM Reasoners)
Foundation Model Prompting: Employing interpretable prompting to bridge the domain gap between user objectives and the outputs of foundation models. Effectively boosting the performance of foundation models on complex tasks through efficient and effective prompting. (PromptAgent)
Semantic Enhancement and Control of Generative Models: Generative models, such as text-to-image models, sometimes exhibit semantic inconsistencies and challenges in control. My aim is to integrate semantic information into the models during training or inference to enhance their semantic fidelity, reliability, and controllability.

Research Overview

My research interests are LLM Augmentation (Prompting, Reasoning), LLM Agent, Unsupervised Learning (Generative Models), and Multi-modal Models. In Prof. Zhiting Hu’s group, I worked on automatic LLM prompt optimization with Zhen. Recently our paper PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization is accepted by ICLR 2024. I am also working on LLM Reasoning by contributing to the LLM Reasoners library, which ensembles the most recent LLM reasoning methods and models. In Prof. Zhuowen Tu’s group, we are working on how to inprove diffusion models’ conceptual performance with an end-to-end loss. During my undergraduate years, I was mentored by Prof. Ying Zhao and worked on Interpretation of Convolutional Neural Networks and Visualization. Here is my graduate thesis: The Research on The Interpretability Method of DeepNeural Network Based on Average Image

How to contact me

Email: xiw136@ucsd.edu (till Jun. 2024) / xywang626@gmail.com

News

Jan 16, 2024	PromptAgent is accepted by ICLR 2024 (The Twelfth International Conference on Learning Representations)!
Nov 17, 2023	PromptAgent’s poster is presented at SoCal NLP 2023 at UCLA, Los Angeles, CA!
Oct 25, 2023	Paper published on Arxiv! PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Sep 1, 2022	Start my Master of Science Computer Science program at UC San Diego!
Jun 1, 2022	Graduate from Central South University!

Selected Publications

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

Xinyuan Wang, Chenxi Li, Zhen Wang, and 6 more authors

[ICLR 2024] The Twelfth International Conference on Learning Representations, 2024

Abs PDF Code Poster

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task. However, automating the generation of such expert-level prompts remains elusive. Existing prompt optimization methods tend to overlook the depth of domain knowledge and struggle to efficiently explore the vast space of expert-level prompts. Addressing this, we present PromptAgent, an optimization method that autonomously crafts prompts equivalent in quality to those handcrafted by experts. At its core, PromptAgent views prompt optimization as a strategic planning problem and employs a principled planning algorithm, rooted in Monte Carlo tree search, to strategically navigate the expert-level prompt space. Inspired by human-like trial-and-error exploration, PromptAgent induces precise expert-level insights and in-depth instructions by reflecting on model errors and generating constructive error feedback. Such a novel framework allows the agent to iteratively examine intermediate prompts (states), refine them based on error feedbacks (actions), simulate future rewards, and search for high-reward paths leading to expert prompts. We apply PromptAgent to 12 tasks spanning three practical domains: BIG-Bench Hard (BBH), as well as domain-specific and general NLP tasks, showing it significantly outperforms strong Chain-of-Thought and recent prompt optimization baselines. Extensive analyses emphasize its capability to craft expert-level, detailed, and domain-insightful prompts with great efficiency and generalizability.
Reduce the medical burden: An automatic medical triage system using text classification BERT based on Transformer structure

Xinyuan Wang, Make Tao, Runpu Wang, and 1 more author

In 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), 2021

Abs PDF

To reduce the pressure of medical triage in the hospitals, this paper proposes a medical triage system that could classify patients’ questions or texts about their symptoms into several given categories to give suggestions on which kind of consulting room patients could choose. First, we have done extensive research on the medical care situation and the hospitals’ problems in China and conclude that reducing the triage pressure is of great importance for hospitals. We then collect the medical Question Answering datasets, including questions and answers with symptom tags. According to the form of our data, we use BERT, a mainstream model in Natural Language Processing, as the base of our system and modify it with additional components specified to our task. We developed two models based on different datasets. One is trained by data from the five most frequent symptom tags. And for the other one, we use the whole dataset by identifying the appearance of special words, measuring the overlap of all the tags, and merging them into 20 categories. Both of them utilize several training techniques and result in relatively high accuracy: top1 85% accuracy and top2 accuracy 96% on the smaller dataset, top1 accuracy 66.2%, and top2 accuracy 78.3% on the other one. Then we analyze the results and build up our web system for medical use. If given real-world data with similar data distribution, our system could help patients judge diseases and alleviate the triage problem in medical treatment to a certain extent. Moreover, a similar strategy of our model could also be adapted for use in different fields like book searching in libraries. Therefore, our system has a broad application prospect.
A Fast Method for Detecting Minority Structures in a Graph

Fangfang Zhou, Qi’an Chen, Yunlong Cui, and 4 more authors

In Proceedings of the 13th International Symposium on Visual Information Communication and Interaction, 2020

Abs PDF

A graph contains plentiful structures. Some minority structures are important, such as high degree nodes and bridges. Detecting these minority structures is beneficial to accelerate computational graph analysis and improve the comprehension of graph visualization. Regarding four typical minority structures, this paper proposes two algorithms to detect these structures fast and efficiently. A set of experiments demonstrate the effectiveness of the proposed algorithms.