Qiyao Ma

Advanced
@Martin-qyma

CS PhD @ UC Davis

martin-qyma.github.io

HERec. [KDD 2026] "Breaking Information Cocoons: A Hyperbolic Graph-LLM Framework for Exploration and Exploitation in Recommender Systems"

16

TRM. From Faithfulness to Correctness: Generative Reward Models that Think Critically

14

Personalized-RewardBench. "Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization"

13

HKU-treasure-miner. COMP2113 Group Project

1

Martin-qyma.github.io. HTML

1
5
Apply