CV
Qinglin Meng
PhD Candidate in Computer Science
Summary
Research in reinforcement learning, large language models, statistical machine learning, multi-armed bandits, and mechanism design.
Education
- Ph.D. in Computer Science2022-08 – May 2027 (expected)Purdue UniversityCourses: Advisor: Steve Hanneke
- B.S. in Mathematical Science2017-08 – June 2022Tsinghua University
Work Experience
- Applied Scientist Intern2026-08 - presentAmazon
- Designed and built an end-to-end product embedding and KNN retrieval pipeline to predict multiple cost and profitability (CP) components for low-volume and cold-start products, reducing prediction MAE by 15–30% across different CP components compared to the existing economics-based baseline.
- Post-trained a Transformer-based embedding model using multi-objective contrastive learning to learn task-specific product representations for similarity-based retrieval and downstream CP component prediction.
- Machine Learning Engineer Intern2026-05 - 2026-08DoorDash
- Formulated incentive allocation as an MDP.
- Developed offline RL algorithms for service quality and incentive cost.
- Built a pipeline covering offline training, evaluation, online experimentation, and serving.
Research and Working Projects
Reward-Free RL for Mechanism Design and Dynamic Pricing Optimization
Advisors: Michael I. Jordan, Zhaoran Wang, and Zhuoran Yang
- Studied online mechanism design with linear function approximation.
- Developed reward-free exploration over a rich policy space to estimate prices.
- Designed optimistic/pessimistic Q-function approximation algorithms to recover mechanisms over repeated interactions while balancing seller and buyer profit.
Adaptive Training Data Allocation for LLM Safety via Non-stationary Bandits
Advisor: Xiangyu Zhang
- Built a data pipeline with OpenFDA drug data, synthetic patient profiles, and generated scenarios for LLM safety evaluation and training.
- Formulated adaptive post-training data selection as a non-stationary multi-armed bandit problem.
- Implemented sliding-window Thompson Sampling to prioritize failure-prone drugs, reducing mean and worst-case error relative to uniform sampling and baseline curricula on LLaMA-3 and Qwen-2.5.
Near-Optimal Bandit Learning for Multiclass Classification
Advisors: Steve Hanneke and Shay Moran
- Proved a sharp Sauer lemma based on the list-DS dimension.
- Developed a chain-of-list learning algorithm achieving near-optimal sample complexity for multiclass learning with bandit feedback.
- Improved an existing list-learning sample complexity bound by a factor of K⁵.
A Survey of Architecture-Level Design for Interpretable LLMs
Advisor: Liangming Pan
- Analyzed architecture-level interpretability techniques, including codebook features, sparse mixture-of-experts architectures, and sparse autoencoder based steering.
Reduction for Multiclass Learning
Advisor: Steve Hanneke
- Studied multiclass reductions with potentially infinite label spaces.
- Developed a representation preserving agnostic-to-realizable reduction by applying a realizable learner to realizable subsets of the input sample.
Academic Service
Reviewer: Transactions on Machine Learning Research (TMLR), COLM 2026, NeurIPS 2026, ACL ARR 2026.
Skills
Programming
- Python
- C++
- R
- MATLAB
- SQL
Software and systems
- PyTorch
- TensorFlow
- Git
- Databricks
- Snowflake
Publications
- PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting2026Advances in Neural Information Processing Systems (NeurIPS 2026)Steve Hanneke, Qinglin Meng, Shay Moran, Amirreza Shaeiri (alphabetical order)
- Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures2026Annual Meeting of the Association for Computational Linguistics (ACL 2026 Main Conference, Oral)Yutong Gao*, Qinglin Meng*, Yuan Zhou, Liangming Pan
- An Optimal Sauer Lemma Over k-ary Alphabets2026arXiv preprint arXiv:2604.12952Steve Hanneke, Qinglin Meng, Shay Moran, Amirreza Shaeiri (alphabetical order)
- Discover, Explain, and Repair: Adaptive Testing of LLM Failures in Medical Safety2026Manuscript under submission, 2026Y. Zhou, S. Guo, Qinglin Meng, X. Zhang
- Representation Preserving Multiclass Agnostic to Realizable Reduction2025International Conference on Machine Learning (ICML 2025)Steve Hanneke, Qinglin Meng, Amirreza Shaeiri (alphabetical order)
- Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach2024Journal of Machine Learning Research (JMLR)Shuang Qiu*, Boxiang Lyu*, Qinglin Meng*, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan
Teaching
- CS 177: Python Programming2023Purdue UniversityRole: Teaching AssistantFall 2023–Fall 2025
- CS 573: Data Mining2023Purdue UniversityRole: Teaching AssistantSpring 2023