Biography
I am currently a Research & Machine Learning Engineer at Shopee, where I work on model development for the retrieval and pre-rank stages of Shopee Search. Before that, I completed both my M.S. and B.S. in Computer Science at Guangdong University of Technology.
I work on recommender systems and causal machine learning, with a focus on generative recommendation and large recommendation models.
Contact
Research Interests
News
Released two new arXiv preprints: ReSID (arXiv:2602.02338) and ManCAR (arXiv:2602.20093).
Published a KDD paper on deep collaborative filtering and released new industry-scale recommendation preprints including OnePiece and ELBO-TDS.
Selected Publications
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
CoRR abs/2602.02338
ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation
CoRR abs/2602.20093
On the probability of necessity and sufficiency of explaining Graph Neural Networks: A lower bound optimization approach
Neural Networks 184:107065
Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering
KDD 2025
OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
CoRR abs/2509.18091
A Probabilistic Framework for Temporal Distribution Generalization in Industry-Scale Recommender Systems
CoRR abs/2511.21032
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
ICML 2024
Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples
AAAI 2024
Collaborators
Work Experience
Research & Machine Learning Engineer
Shopee, Search, Recommendation & Ads
2024 - Present
Working on model development for the retrieval and pre-rank stages of Shopee Search, with emphasis on industrial recommendation modeling, temporal generalization, and production iteration.
Service
Reviewer
NeurIPS, AAAI, SIGIR, and related venues.