Zhengyang Sun — accepted AI-conference papers

2026

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Zhengyang Sun, Yu Chen, Xin Zhou, Xiaofan Li, Xiwu Chen, Dingkang Liang +1

CVPR 2026

Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA, a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsi

Cited by 0 Source ↗code ↗Scholar ↗

2022

INT: Towards Infinite-Frames 3D Detection with an Efficient Framework

Jianyun Xu, Zhenwei Miao, Da Zhang, Hongyu Pan, Kaixuan Liu, Peihan Hao +4

ECCV 2022poster

"It is natural to construct a multi-frame instead of a single-frame 3D detector for a continuous-time stream. Although increasing the number of frames might improve performance, previous multi-frame studies only used very limited frames to build their systems due to the dramatically increased comput…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗