I am currently a Ph.D. student since 2023, advised by Prof.Peidong Liu, at the School of Engineering, Westlake University in collaboration with Zhejiang University, Hangzhou, China. My previous research focused on geometry and optimization problems in 3D Computer Vision. Recently, I have been attempting to build an intelligent agent, TIC, in a probability space. This framework involves three core sub-tasks: Transport (learning the dynamics of probability), Inference (inferring probability from observations), and Control (steering probability towards a target). Although these three tasks may seem independent, I hope to model and solve them under a unified language. This may give rise to a completely new interdisciplinary field that combines Generation (Diffusion Models, Flow Matching), Control (Stochastic Optimal Control, Reinforcement Learning), Sampling, Transport (Schrödinger Bridge, Trajectory Inference, Optimal Transport), Game (Mean Field Game), and Global Optimization.

Previously, I obtained my Bachelor’s degree in the College of Electrical and Information Engineering from Hunan University, Changsha, China.

I also served as a reviewer for the CVPR, ICCV, NeurIPS, AAAI, ACM MM, 3DV, ICRA, IROS and RAL.

News

Notes

Publications

Selected publications I am a primary author on are highlighted.

Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning Jiayao Mai*, Bangyan Liao*, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera, Tailin Wu, Yi Zhou, Peidong Liu ICLR 2026 [ Paper | BibTex ]

scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction Chenglei Yu*, Chuanrui Wang*, Bangyan Liao, Tailin Wu ICLR 2026 [ Paper | BibTex ]

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization Wenpu Li*, Bangyan Liao*, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu NeurIPS 2025 [ Paper | Preprint | BibTex | Poster | Project page | Code ]

Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World Bangyan Liao*, Zhenjun Zhao*, Haoang Li, Yi Zhou, Yingping Zeng, Hao Li, Peidong Liu CVPR 2025   (Full Score)   (Oral Presentation)   (Best Paper Candidate) [ Paper | Preprint | BibTex | Code ]

DaCapo: Score Distillation as Stacked Bridge for Fast and High-quality 3D Editing Yufei Huang, Bangyan Liao, Yuqi Hu, Haitao Lin, Lirong Wu, Siyuan Li, Cheng Tan, Zicheng Liu, Yunfan Liu, Zelin Zang, Chang Yu, Zhen Lei CVPR 2025 [ Paper | BibTex ]

Ego-motion Estimation for Vehicles with a Rolling Shutter Camera Yongcong Zhang, Bangyan Liao, Delin Qu, Junde Wu, Xinyu Lu, Wanting Li, Yifei Xue, Yizhen Lao TIV 2024 [ Paper | BibTex ]

RSL-BA: Rolling Shutter Line Bundle Adjustment Yongcong Zhang* , Bangyan Liao* , Yifei Xue, Chen Lu, Peidong Liu, Yizhen Lao ECCV 2024 [ Paper | BibTex | Project page ]

GlobalPointer: Large Scale Plane Adjustment with Bi-Convex Relaxation Bangyan Liao*, Zhenjun Zhao*, Lu Chen, Haoang Li, Daniel Cremers, Peidong Liu ECCV 2024 [ Paper | Preprint | BibTex | Talk video | Project page ]

Motion and Structure from Event-based Normal Flow Zhongyang Ren* , Bangyan Liao*, Delei Kong , Jinghang Li , Peidong Liu , Laurent Kneip, Guillermo Gallego , Yi Zhou ECCV 2024 [ Paper | Preprint | BibTex | Talk video | Project page ]

Event-Aided Time-to-Collision Estimation for Autonomous Driving Jinghang Li*, Bangyan Liao*, Xiuyuan Lu, Peidong Liu, Shaojie Shen, Yi Zhou ECCV 2024 [ Paper | Preprint | BibTex | Talk video | Project page ]

Fast Rolling Shutter Correction in the Wild Delin Qu*, Bangyan Liao*, Huiqing Zhang, Omar Ait-Aider, Yizhen Lao TPAMI 2023 [ Paper | Preprint | BibTex | Project page | Code ]

Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution Bangyan Liao*, Delin Qu*, Yifei Xue, Huiqing Zhang, Yizhen Lao CVPR 2023 [ Paper | Preprint | BibTex | Talk video | Project page | Code ]