Yikun Han

I am an incoming PhD student in Information Sciences at the University of Illinois Urbana-Champaign. Previously, I received my Master's degree in Data Science from the University of Michigan.

My research interests span the intersection of geometric deep learning, natural language processing, and AI for healthcare.

I am fortunate to be advised by Prof. Halil Kilicoglu and Prof. Yue Guo at UIUC. During my time at Michigan, I was part of the CASI Lab, supervised by Prof. Ambuj Tewari, and closely collaborated with the AI Health Lab at the University of Texas at Austin.

Email  /  GitHub  /  Curriculum Vitae  /  Google Scholar  /  LinkedIn

Publications

Teaching Machine Olfaction in an Undergraduate Deep Learning Course: An Interdisciplinary Approach Based on Chemistry, Machine Learning, and Sensory Evaluation

We integrated machine olfaction into an undergraduate deep learning course, introducing smell as a new modality alongside traditional data types. Hands-on activities and graph neural networks enhanced student engagement and comprehension. We discuss challenges and future improvements.

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation

We present TinyLLM, a knowledge distillation approach that transfers reasoning abilities from multiple large language models (LLMs) to smaller ones. TinyLLM enables smaller models to generate both accurate answers and rationales, achieving superior performance despite a significantly reduced model size.

Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models

We explore prompt sensitivity in large language models (LLMs), where semantically identical prompts can yield vastly different outputs. By modeling this sensitivity as generalization error, we improve uncertainty calibration using paraphrased prompts. Additionally, we propose a new metric to quantify uncertainty caused by prompt variations, offering insights into how LLMs handle semantic continuity in natural language.

When Large Language Models Meet Vector Databases: A Survey

We survey the integration of Large Language Models (LLMs) and Vector Databases (VecDBs), highlighting VecDBs’ role in addressing LLM challenges like hallucinations, outdated knowledge, and memory inefficiencies. This review outlines foundational concepts and explores how VecDBs enhance LLM performance by efficiently managing vector data, paving the way for future advancements in data handling and knowledge extraction.

A Community Detection and Graph-Neural-Network-Based Link Prediction Approach for Scientific Literature

We integrate the Louvain community detection algorithm with various GNN models to improve link prediction in scientific literature networks. This approach consistently boosts performance, with models like GAT seeing AUC increases from 0.777 to 0.823, demonstrating the effectiveness of combining community insights with GNNs.

A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge

We review key algorithms for solving approximate nearest neighbor search in vector databases, categorizing them into hash-based, tree-based, graph-based, and quantization-based methods. Additionally, we discuss challenges and explore how vector databases can integrate with large language models for new opportunities.

Competitions

DREAM Olfactory Mixtures Prediction Challenge

We use pre-trained graph neural networks and boosting techniques to enhance odor mixture discriminability, transforming single molecule embeddings into mixture predictions with improved robustness and accuracy.

Research Internships

University of Michigan (Aug. 2023 - Now)

Advisor: Prof. Ambuj Tewari

Research Topics:

[1] Graph Neural Networks

[2] Molecular Property Prediction

[3] Protein-Ligand Affinity Prediction

University of Texas at Austin (Feb. 2024 - Now)

Advisor: Prof. Ying Ding, Prof. Jiliang Tang

Research Topics:

[1] Graph Retrieval-Augmented Generation

[2] Medical AI

[3] Collaborator Recommendation

University of Notre Dame (Dec. 2023 - Mar. 2024)

Advisor: Prof. Nitesh V. Chawla

Research Topics:

[1] Knowledge Distillation

[2] Multi-Teacher Collaboration

[3] In-Context Learning

Tianyuan Mathematical Center in Southwest China (May. 2022 - Nov. 2022)

Advisor: Prof. Gang Chen

Research Topics:

[1] LAPACK Optimization

[2] Parallel Computation for Large-Scale Matrices

[3] High-Performance Matrix Factorization and Back Substitution

Education

University of Michigan (Aug. 2023 - May. 2025)

Master

Data Science

GPA: 3.894/4.0

Sichuan University (Sep. 2019 - Jun. 2023)

Bachelor

Information Resources Management

GPA: 3.87/4.0

Rank: 2/76

Awards

Book List

Design and source code from Jon Barron's website