Biography
Xuhui (Daniel) Zhan is a Data Scientist and Machine Learning Engineer with extensive experience in NLP, computer vision, multimodal AI, and MLOps. Recently graduated with a Master’s in Data Science from Vanderbilt University (GPA: 3.98/4.0), he combines robust theoretical knowledge with practical, real-world applications.
At Vanderbilt University’s AI Negotiation Lab, as Lead AI & Data Science Researcher, Xuhui developed an LLM pipeline that auto-codes negotiation transcripts, dramatically reducing costs by over 99% while increasing human-model agreement from 30% to 80%. His work has been presented at prestigious venues including the 2025 AI Negotiation Summit (Harvard/MIT).
In his role as a Graduate Research Assistant at Vanderbilt’s Network and Data Science Lab, Xuhui designed innovative fusion frameworks integrating vision, graph, and language modalities. He refactored LLaVA to reduce compute costs by 25% while matching SOTA accuracy, and built a TGAT-LLM pipeline that aims to outperform token-level integration methods.
As a Professional Research Assistant, he boosted ancient-mortar classification accuracy from 60% to 97% using Vision Transformers and invented a vision-only provenance algorithm that reduced analysis time from months to minutes.
Prior to Vanderbilt, as an Algorithm Development Engineer, Xuhui shipped a computer vision storage-detection system to approximately 30 warehouses, increasing pick accuracy by 15% and reducing manual checks by 80%. He also optimized ROS localization algorithms and standardized deployment toolchains for company-wide rollouts.
Xuhui earned his Bachelor’s degree in Data Science with First Class Honours and Highest Distinction from Beijing Normal-Hong Kong Baptist University, showcasing his commitment to academic excellence.
“Any sufficiently advanced technology is indistinguishable from magic.”
— Arthur C. Clarke, Clarke’s Third Law
- Large Language Model
- Computer Vision
- Multi-modality Model
- Graph Neural Network
- Recommender System
MSc in Data Science, 2023-2025
Vanderbilt University
BSc in Data Science, 2018-2022
Beijing Normal-Hong Kong Baptist University
BSc in Data Science, 2018-2022
Hong Kong Baptist University
Experience
Advisor: Prof. Ray Friedman
- Drive end‑to‑end LLM research for negotiation science—designing, experimenting, and optimising models.
- Built an LLM pipeline that auto-codes negotiation transcripts, cutting per-transcript cost from $5,000 to $3 (>99% savings) and boosting human–AI agreement from 30% to 80%.
- Developed a novel algorithm that injects population-level variation into LLM negotiator agents, yielding realistic and diverse subject pools for negotiation studies.
- Lead the full ML lifecycle—from data engineering through Web deployment—while collaborating closely with negotiation scholars and data-science peers.
- Work presented at the 2025 AINegotiationSummit (Harvard/MIT) and the International Association for Chinese Management Research annual meeting.
Advisor: Prof. Tyler Derr
- Developed a unified multimodal fusion framework integrating vision, graph, and language modalities:
- Vision–Language: Refactored LLaVA architecture, eliminating the projection pre-training stage, resulting in a 25% reduction in training time and halving data requirements while maintaining comparable performance across nine benchmarks.
- Graph–Text: Implemented a Temporal Graph Attention Network (TGAT)–LLM pipeline capable of generating high-quality textual attributes for social networks. Empirically evaluated performance on the Venmo Dataset, with extensive experiments on the Amazon Review Dataset forthcoming.
Graduate Teaching Fellowship
Responsible for organizing labs, creating quizzes, grading materials and hosting office hours.
Graduate level:
- DS 5620: Probability and Statistical Inference
- DS 5690: Gen AI in Theory and Practice
Undergrad level:
- DS 3100: Fundamentals of Data Science
Advisor: Prof. Markus Eberl
- Boosted ancient-mortar classification accuracy from 60% to 97% with Vision Transformers on 10M images.
- Invented a vision-only provenance algorithm, reducing similarity -analysis runtime from months to minutes; manuscript in preparation for Nature Methods.
Work as an algorithm engineer and take in charge of all machine learning applications and efficient data analysis.
Responsibilities include:
- Optimize the end localizer program and deploy on new products (ROS)
- Develop the vision algorithm for detecting whether two shelves are aligned (opencv, pytorch)
- Develop the end-to-end storage status detection system, implement the whole pipeline including data collection, data labeling, model training, model deployment, database construction, communication policies and api for updating status to central server (WCS) and display results on the front-end website with scaling abilities to aggregate and update results in real-time on constraint computation resources and deployment process (roboflow, django, redis, celery, pytorch, ONNX)