Chao Cui — accepted AI-conference papers

2025

Calibrating Video Watch-time Predictions with Credible Prototype Alignment

Chao Cui, Shisong Tang, Fan Li, Jiechao Gao, Hechang Chen

ICML 2025poster

Accurately predicting user watch-time is crucial for enhancing user stickiness and retention in video recommendation systems. Existing watch-time prediction approaches typically involve transformations of watch-time labels for prediction and subsequent reversal, ignoring both the natural distributio…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu, Chao Cui, Vasant G Honavar

EMNLP 2024main

This paper introduces a novel generalized self-imitation learning GSIL framework, which effectively and efficiently aligns large language models with offline demonstration data. We develop GSIL by deriving a surrogate objective of imitation learning with density ratio estimates, facilitating the use…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗