Chao Zhang

My research lies in the areas of data science, machine learning, and AI. My goal is to make it easier to build domain-customized foundation models and AI agents for task-solving and decision-making. My technical efforts centers on addressing key challenges in data efficiency, computation efficiency, and model robustness. On the application front, I am deeply interested in harnessing foundation models to advance AI for science.

Currently, I am working on the following themes:

1. Data-Centric LLM – Adapting Large Language Models for target domains by addressing data scarcity challenges through data-efficient methods such as learning from weak supervision and active learning.
2. LLM Agents & Reasoning – Improving LLM reasoning and planning abilities by enabling them to learn and evolve through interaction with external environments for feedback. The goal is to better adapt LLMs and enhance their reasoning capabilities without expensive manual curation of fine-tuning data.
3. AI Alignment – Ensuring responsible and reliable deployment of AI through critical techniques including uncertainty quantification, enhancing LLM factuality, and improving LLM alignment.
4. AI for Science – Leveraging foundation models and AI agents to accelerate scientific discovery in diverse fields such as material science, biomedical and life sciences, and urban science.

Acknowledgment: My work has been generously supported by research funding/gift from NSF (IIS CAREER-2144338, IIS-2106961, IIS-2008334), ONR MURI , Kolon, HomeDepot, ADP, and Adobe. My work has also been recognized by an NSF CAREER Award, a Facebook Faculty Award, an Amazon AWS Machine Learning Research Award, a Google Faculty Research Award, a Kolon Faculty Fellowship, an ACM SIGKDD Dissertation Runner-up Award, and several paper awards from IMWUT (UbiComp), ECML/PKDD, and ML4H.

We aim to adapt LLMs to various domains and complex tasks. A key bottleneck when adapting LLMs is data scarcity – the lack of high-quality, representative data for the target domain. We are tackling this bottleneck by developing methods for data-efficient LLM adaptation, including:

• Learning from Noisy Data and Weak Supervision: To address the lack of data for LLM fine-tuning, we explore using weaker forms of supervision signals that are easier to collect (e.g., labeling rules, LLM supervision, pseudo labels).
  • DyGen: Fine-Tuning Language Models with Noisy Labels by Dynamics-Enhanced Generative Modeling, KDD'23
  • Fine-Tuning Pre-trained Language Model with Weak Supervision, NAACL'21
  • Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition, KDD'22
  • Text Classification Using Label Names Only: A Language Model Self-Training Approach, EMNLP'20
  • BOND: Bert-Assisted Open-Domain Named Entity Recognition with Distant Supervision, KDD'20
  • Weakly-Supervised Neural Text Classification, CIKM'18
• More Efficient Data Curation: We develop techniques for fine-tuning LLMs with active learning, by strategically selecting data instances for curation to improve fine-tuning performance.
  • Cold-start Data Selection for Better Few-shot Fine-tuning of Pretrained Language Models, ACL'23
  • PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning, ACL'22
  • AcTune: Uncertainty-Aware Active Self-Training for Active Fine-Tuning of Language Models, NAACL'22

We investigate improving LLM reasoning and planning abilities by enabling them to evolve through interaction with external environments for feedback. The goal is to better adapt LLMs and enhance their reasoning capabilities without expensive manual curation of fine-tuning data.

• Adapting LLM Agents with Universal Feedback Through Communication, NAACL'25
• Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training, NAACL'25
• BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models, ICML'24
• ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search, ICLR'24
• AdaPlanner: Adaptive Planning from Feedback with Language Models, NeurIPS'23
• ToolQA: A Dataset for LLM Question Answering with External Tools, NeurIPS'23

We aim to develop AI systems that are not only capable but also trustworthy for deployment in various domains. We study the following topics in the space of trustworthy AI: uncertainty quantification, LLM factuality, and LLM alignment.

• Uncertainty Quantification for Deep Learning: Uncertainty-aware ML models are crucial for building trustworthy AI systems. Many deep learning models produce uncertainty-agnostic point estimates or miscalibrated distributions. We are addressing this issue by designing techniques for quantifying uncertainty in deep learning models. We also study decision-focused learning under uncertainty to make learning informed by downstream decision-making tasks.
  • Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints, AISTATS'25
  • When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting, KDD'23
  • End-to-end Stochastic Programming with Energy-based Model, NeurIPS'22
  • When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting, NeurIPS'21
  • SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates, ICML'20
  • RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations, UbiComp'18

• LLM Factuality and RAG: We develop methods to enhance the factual accuracy of LLMs through more robust and intelligent retrieval-augmented generation (RAG) and context ranking.
  • RankRAG: Unifying Retrieval-Augmented Generation and Context Ranking in LLMs, NeurIPS'24
  • ARL2: Aligning Retrievers with Black-box Large Language Models via Self-guided Adaptive Relevance Labeling, ACL'24
  • COCO-DR: Combating the Distribution Shift in Zero-Shot Dense Retrieval with Contrastive and Distributional Robust Learning, EMNLP'22
• LLM Alignment and Robust Fine-Tuning: We investigate robust fine-tuning methods for LLMs to improve generalization on out-of-distribution data, as well as identifying vulnerabilities in LLMs and scalably aligning them:
  • Self-Generated Critiques Boost Reward Modeling for Language Models, NAACL'25
  • Aligning Large Language Models with Representation Editing: A Control Perspective, NeurIPS'24
  • Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias, NeurIPS'23
  • Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data, EMNLP'20

We aim to leverage AI and foundation models for advancing scientific discovery. We develop domain-specific foundation models and LLM agents for different scientific domains. On the application side, we collaborate with domain-experts to advance scientific discovery in material design, biomedical and life science, and urban science:

• AI for Material Science:
  • Efficient Evolutionary Search Over Chemical Space with Large Language Models, ICLR'25
  • LLMatDesign: Autonomous Materials Discovery with Large Language Models, preprint
  • May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations, NeurIPS'23
  • Autoregressive Diffusion Model for Graph Generation, ICML'23
  • MUBen: Benchmarking the Uncertainty of Pre-Trained Models for Molecular Property Prediction, TMLR'24
  • POLYIE: A Dataset of Information Extraction from Polymer Material Scientific Literature, NAACL'24

• AI for Biomedical and Life Science:
  • Contrastive Fitness Learning: Reprogramming Protein Language Models for Low-N Learning of Protein Fitness Landscape, RECOMB'24
  • TransEHR: Self-Supervised Transformer for Clinical Time Series Data, ML4H'23
  • When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting, NeurIPS'21
  • ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select, EMNLP'22
• AI for Urban Science:
  • T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction, IEEE ITS'20
  • A Linear Time Approach to Computing Time Series Similarity based on Deep Metric Learning, TKDE'20
  • DeepMove: Predicting Human Mobility with Attentional Recurrent Networks, WWW'18

• 2024 GaTech CoC Outstanding Junior Faculty Award
• 2022 NSF Career Award
• 2022 ML4H Outstanding Paper Award
• 2021 Facebook Faculty Research Award
• 2021 Kolon Faculty Fellowship
• 2020 Amazon AWS Machine Learning Research Award
• 2020 Google Faculty Research Award
• 2019 ACM SIGKDD Dissertation Award Runner-up
• 2018 ACM IMWUT Distinguished Paper Award
• 2015 ECML/PKDD Best Student Paper Runner-up Award
• 2013 Chiang Chen Overseas Graduate Fellowship

(* denotes equal contribution)

• CX4240: Introduction to Computational Data Analysis
• CSE8803-DLT: Deep Learning for Text Data

Prospective students: I am always looking for strong and motivated students to join our group. If you are interested in working with me, you can either email me or fill out this form.

Current:

• Rui Feng: Ph.D. Student in CS
• Yuchen Zhuang: Ph.D. Student in ML
• Yinghao Li: Ph.D. Student in ML
• Rongzhi Zhang: Ph.D. Student in ML
• Haotian Sun: Ph.D. Student in ML (co-advised with Bo Dai)
• Kuan Wang: Ph.D. Student in CSE
• Haorui Wang: Ph.D. Student in CSE
• Agam A. Shah: Ph.D. Student in ML (co-advised with Sudheer Chava)
• Rushi Qiang: Ph.D. Student in CSE (co-advised with Bo Dai)
• Changhao Li: Ph.D. Student in CSE (co-advised with Bo Dai)

Alumni:

• Yue Yu: Ph.D., 2024 (–> Research Scientist @ Meta GenAI Team)
• Lingkai Kong: Ph.D., 2024 (–> Postdoc Fellow @ Harvard)
• Yanbo Xu: Ph.D., 2023 (–> Research Scientist @ Microsoft Research)
• Binghong Chen: Ph.D., 2023 (–> Quant @ Citadel Capital, co-advised with Prof. Le Song)
• Pranav Shetty: Ph.D., 2023 (–> Research Scienctist @ JP Morgan Chase, JP Morgan AI Ph.D. Fellowship, co-advised with Prof. Rampi Ramprasad)
• Yi Rong: Visiting Ph.D. Student
• Vidit Jain: M.S. Student in CS
• Mukund Rungta: M.S. Student in CS
• Junyang Zhang: M.S. Student in CS
• Piyush Patil: M.S. Student in CS
• Mengyang Liu: M.S. Student in CSE
• Isaac Rehg: M.S. in CS
• Wendi Ren: M.S. in CSE
• Ruijia Wang: M.S. in CSE
• Jacob Wessell: M.S. in CS
• Wenhao Mu: M.S. in CS
• Shangqing Xu: M.S. in CS