Yingping Zeng — accepted AI-conference papers

2026

Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning

Jiayao Mai, Bangyan Liao, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera +3

ICLR 2026poster

The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on…

Cited by 0 Source ↗Scholar ↗

2025

Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World

Bangyan Liao, Zhenjun Zhao, Haoang Li, Yi Zhou, Yingping Zeng, Hao Li +1

CVPR 2025award

Determining the vanishing points (VPs) in a Manhattan world, as a fundamental task in many 3D vision applications, consists of jointly inferring the line-VP association and locating each VP. Existing methods are, however, either sub-optimal solvers or pursuing global optimality at a significant cost…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗