About Me
I am an Assistant Professor and Presidential Young Fellow at the School of Data Science (SDS), The Chinese University of Hong Kong, Shenzhen (CUHKSZ) since Aug 2024. I am looking for PhD students, RAs, and visiting students/interns. Please feel free to reach out if you're interested in working with me.
I work on both the theory and practice of AI/machine learning. On the practical side, I'm mostly interested in large language models (LLMs), including LLM-based agents, personalization of LLMs, LLM routing, prompt optimization, and RLHF/DPO, all of which can be studied from the perspective of multi-armed bandits (MAB) and Bayesian optimization (BO). On the theoretical side, I'm mainly interested in the theoretical study of MAB and BO.
From Jan 2024 to Jun 2024, I worked as a Postdoctoral Associate at MIT, Laboratory for Information and Decision Systems (LIDS), advised by Prof. Patrick Jaillet. From 2021 to 2023, I was a Postdoctoral Fellow at the National University of Singapore (NUS) with Prof. Bryan Kian Hsiang Low. I obtained my Ph.D. in Computer Science from NUS (2017-2021), co-advised by Prof. Bryan Kian Hsiang Low (NUS) and Prof. Patrick Jaillet (MIT). My Ph.D. study was supported by Singapore-MIT Alliance for Research and Technology (SMART) Graduate Fellowship. In 2015, I obtained my undergraduate degree from NUS, Electrical Engineering with first class honors.
News
- Sep 2025 Two papers accepted to NeurIPS 2025!
- Aug 2025 Invited to serve as an Area Chair for ICLR 2026!
- May 2025 Our paper on LLM source attribution & watermaking accepted to ACL 2025 Findings!
- May 2025 2 papers accepted to ICML 2025!
- Apr 2025 Invited to serve as an Area Chair for NeurIPS 2025!
- Apr 2025 Our paper on Bayesian optimization accepted to Journal of Machine Learning Research (JMLR)!
Selected Workshop Papers & Preprints
* denotes equal contribution, † denotes corresponding author, 🎓 denotes my students.
-
T-POP: Test-Time Personalization with Online Preference Feedback.
Preprint, 2025. [arXiv]
-
FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits.
Preprint, 2025. [arXiv]
-
Meta-Prompt Optimization for LLM-Based Sequential Decision Making.
ICLR 2025 Workshop on Reasoning and Planning for Large Language Models. [arXiv]
-
Large Language Model-Enhanced Multi-Armed Bandits.
ICLR 2025 Workshop on Reasoning and Planning for Large Language Models. [arXiv]
-
Federated Linear Dueling Bandits.
Preprint, 2025. [arXiv]
-
Active Human Feedback Collection via Neural Contextual Dueling Bandits.
ICLR 2025, Workshop on on Bidirectional Human-AI Alignment. [arXiv]
-
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment.
Preprint, 2025. [arXiv]
-
Prompt Optimization with Human Feedback.
ICML 2024 Workshop on Models of Human Feedback for AI Alignment. (Selected as Oral) [arXiv]
-
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients.
ICML 2024 Workshop on Differentiable Almost Everything. [arXiv]
Publications
* denotes equal contribution, † denotes corresponding author, 🎓 denotes my students.
-
Convergence Rates of Constrained Expected Improvement.
NeurIPS 2025 (Spotlight). [arXiv]
-
Adaptive Sample Scheduling for Direct Preference Optimization.
NeurIPS 2025. [arXiv]
-
Source Attribution for Large Language Model-Generated Data.
ACL Findings 2025 [arXiv]
-
Online Clustering of Dueling Bandits.
ICML 2025 [arXiv]
-
Refining Adaptive Zeroth-Order Optimization at Ease.
ICML 2025 [arXiv]
-
Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization.
Journal of Machine Learning Research (JMLR), 2025 [Paper]
-
Neural Dueling Bandits: Principled Preference-Based Optimization with Non-Linear Reward Function.
ICLR 2025 [arXiv]
-
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars.
NeurIPS 2024 [arXiv]
-
Localized Zeroth-Order Prompt Optimization.
NeurIPS 2024 (Spotlight) [arXiv]
-
Data-Centric AI in the Age of Large Language Models.
EMNLP Findings 2024 [arXiv]
-
Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers.
-
Robustifying and Boosting Training-Free Neural Architecture Search.
ICLR 2024 [arXiv]
-
Batch Bayesian Optimization For Replicable Experimental Design.
NeurIPS 2023 [Paper]
-
Exploiting Correlated Auxiliary Feedback in Parameterized Bandits.
NeurIPS 2023 [Paper]
-
Training-Free Neural Active Learning with Initialization-Robustness Guarantees.
ICML 2023 [Paper]
-
ICLR 2023 [Paper]
-
Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation.
ICLR 2023 [Paper]
-
Recursive Reasoning-Based Training-Time Adversarial Machine Learning.
Artificial Intelligence Journal, 2023 [Paper]
-
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search.
NeurIPS 2022 [arXiv]
-
Bayesian Optimization under Stochastic Delayed Feedback.
ICML 2022 [Paper]
-
On Provably Robust Meta-Bayesian Optimization.
UAI 2022 [Paper]
-
Neural Ensemble Search via Bayesian Sampling.
UAI 2022 [Paper]
-
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization.
ICLR 2022 [arXiv]
-
Differentially Private Federated Bayesian Optimization with Distributed Exploration.
-
Optimizing Conditional Value-At-Risk of Black-Box Functions.
-
Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee.
-
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games.
-
Implicit Posterior Variational Inference for Deep Gaussian Processes.
Awards and Honors
- Presidential Young Fellow, The Chinese University of Hong Kong, Shenzhen, 2024
- Dean's Graduate Research Excellence Award, NUS, School of Computing, 2021
- Research Achievement Award, NUS, School of Computing, 2019 & 2020 (Twice)
- Singapore-MIT Alliance for Research and Technology (SMART) Graduate Fellowship, 2017
- ST Electronics Prize (Top student in cohort), NUS, 2012 & 2013 (Twice)
- Dean’s List, NUS, 2011-2015 (Five times)
Professional Service
- Area Chair: NeurIPS 2025, ICLR 2025 & 2026
- Conference Reviewer: NeurIPS, ICML, ICLR, UAI, AISTATS, AAAI, CoRL, CVPR, ICCV, AAMAS, IROS, ICRA.
- Journal Reviewer: IEEE TPAMI, Operations Research, SIAM Journal on Optimization, Automatica, TMLR, Neural Networks, IEEE RA-L.