Chao Zhang

My research lies in the areas of data science, machine learning, and AI. My goal is to build advanced large language models and AI agents for complex task-solving and decision-making. My technical efforts center 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. LLM Post-Training Data and Algorithms for Agents – Developing efficient post-training methods for adapting and fine-tuning LLMs to create intelligent agents that can learn from experience, interact with environments, and improve their reasoning and agentic capabilities.
2. AI Safety and Trustworthy AI – Facilitating responsible and reliable deployment of AI systems through critical techniques including uncertainty quantification, enhancing LLM factuality, improving LLM alignment, and developing robust methods for building trustworthy AI agents.
3. Datasets, Evaluation, and Benchmarks – Creating comprehensive evaluation frameworks, datasets, and benchmarks for assessing AI system performance, particularly focusing on agent capabilities, reasoning abilities, and real-world task completion across diverse domains.
4. AI for Scientific Discovery – Developing foundation models and AI agents to accelerate scientific discovery, with applications in diverse fields such as time series analysis, material science, biomedical and life sciences.

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 investigate improving LLM reasoning and agentic abilities by enabling them to evolve through interaction with external environments for feedback. The goal is to better adapt LLMs and enhance their reasoning and agentic capabilities through efficient post-training data collection and algorithmic innovations.

• 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

We aim to develop AI systems that are not only capable but also trustworthy for deployment in various domains. We study LLM factuality (e.g., RAG, agentic search), uncertainty, and alignment.

• Self-Generated Critiques Boost Reward Modeling for Language Models, NAACL'25
• Aligning Large Language Models with Representation Editing: A Control Perspective, NeurIPS'24
• 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
• 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 develop new datasets, benchmarks, and evaluation protocols for training and assessing LLM performance, with particular focus on agent capabilities, reasoning abilities, and real-world task completion.

• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering, arXiv'25
• Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis, NeurIPS'24
• 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
• ToolQA: A Dataset for LLM Question Answering with External Tools, NeurIPS'23

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:

• 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
• Contrastive Fitness Learning: Reprogramming Protein Language Models for Low-N Learning of Protein Fitness Landscape, RECOMB'24
• T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction, IEEE ITS'20

This section includes our previous work on weak supervision, active learning, and uncertainty quantification for language models and traditional machine learning tasks.

• Learning from Noisy Data and Weak Supervision: Our foundational work on addressing data scarcity challenges through weak supervision and noisy label learning for smaller language models and traditional NLP tasks.
  • 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
• Active Learning and Data Curation: Techniques for efficient data selection and curation to improve model performance with limited labeled data.
  • 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

• 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

• 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)

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:

• Agam A. Shah: Ph.D. Student in ML (co-advised with Sudheer Chava)
• Changhao Li: Ph.D. Student in CSE (co-advised with Bo Dai)
• Haorui Wang: Ph.D. Student in CSE
• Haotian Sun: Ph.D. Student in ML (co-advised with Bo Dai)
• Jing Peng: Ph.D. Student in CSE
• Kuan Wang: Ph.D. Student in CSE
• Rui Feng: Ph.D. Student in CS
• Rushi Qiang: Ph.D. Student in CSE (co-advised with Bo Dai)
• Yanbin Yin: Ph.D. Student in CS

Alumni:

• Yuchen Zhuang: Ph.D. Student in ML (–> Research Scientist @ Google Deepmind)
• Yinghao Li: Ph.D. Student in ML (–> Research Scientist @ Amazon AWS)
• Rongzhi Zhang: Ph.D. Student in ML (–> Research Scientist @ Amazon Rufus Team)
• 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