Mingyang Du — accepted AI-conference papers

2026

UniFuture: A 4D Driving World Model for Future Generation and Perception

Dingkang Liang, Dingyuan Zhang, Xin Zhou, Sifan Tu, Tianrui Feng, Xiaofan Li +4

ICRA 2026poster

We present UniFuture, a unified 4D Driving World Model designed to simulate the dynamic evolution of the 3D physical world. Unlike existing driving world models that focus solely on 2D pixel-level video generation (lacking geometry) or static perception (lacking temporal dynamics), our approach brid…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models

Hongkai Lin, Dingkang Liang, Mingyang Du, Xin Zhou, Xiang Bai

NeurIPS 2025poster

Generative depth estimation methods leverage the rich visual priors stored in pretrained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic degradation in the image generation capability of the pretrained mo…

Cited by 0 Source ↗Scholar ↗