About Me
Bio
I am an Applied Scientist at Amazon, working on LLM-based agentic reasoning systems and adaptive decision-making pipelines. My research spans identifiable representation learning, signal processing, matrix factorization, contextual bandits, and non-convex optimization.
I received my Ph.D. from the Department of Computer & Information Science & Engineering (CISE) at the University of Florida, where I was advised by Prof. Kejun Huang. Before joining UF, I received my bachelor’s degree from Nanjing University.
Research Focus
Machine Learning Foundations
Representation learning with identifiability guarantees, non-convex optimization, and latent variable modeling.
Adaptive Decision Systems
Contextual neural bandits, learning from partial feedback, and uncertainty-aware decision-making for ML systems at scale.
LLM & Agentic Reasoning Systems
Routing, orchestration, evaluation, and control for multi-component systems built on large language models.
Selected Research & System Contributions
Research
- Established identifiability results for latent representation learning models, including bounded component analysis and dictionary learning.
- Developed non-convex optimization methods with theoretical guarantees for identifiable latent representation learning problems.
Applied ML Systems
- Built uncertainty-aware decision methods for recommendation systems with partial feedback.
- Developed routing and orchestration strategies for LLM-based systems.
- Worked on system-level control and decision quality under practical constraints.
Selected Publications
Global Identifiability of L1-based Dictionary Learning via Matrix Volume Optimization
Establishes global identifiability guarantees for L1-based dictionary learning via a matrix-volume formulation.
Identifiable Bounded Component Analysis via Minimum Volume Enclosing Parallelotope
Introduces a minimum-volume enclosing parallelotope view for identifiable bounded component analysis.
Complex Bounded Component Analysis: Identifiability and Algorithm
Provides identifiability analysis and an efficient algorithm for complex-valued bounded component analysis.
Academic Service
- Conference reviewer: NeurIPS, ICML, ICLR, AISTATS, AAAI, ICASSP, MLSP, IJCNN.
- Journal reviewer: IEEE Transactions on Signal Processing (TSP), Journal of Machine Learning Research (JMLR).
Beyond Research
Mentoring · Side Projects · Other Interests
A separate, lightweight page leaves room for work and interests that do not fit naturally into a research summary.