Zeqi Zhou — accepted AI-conference papers

2026

Distilling Geometry Priors for 3D-Consistent Video Generation

Hongyang Du, Hongyang Du, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal +4

ICML 2026poster

While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit ince…

Cited by 0 Source ↗Scholar ↗

2026

Proteo-R1: Thinking Foundation Models for De Novo Protein Binder Design

Fang Wu, Li Erran Li, Weihao Xuan, Heli Qi, Zeqi Zhou, Hanqun CAO +23

ICML 2026poster

Recent advances in generative diffusion and flow-matching models have revolutionized molecular design, enabling the creation of novel proteins, small molecules, and RNA sequences with unprecedented fidelity. Yet, these models remain intuitive rather than intelligent—they generate without reasoning. …

Cited by 0 Source ↗Scholar ↗