I’m Ye Tian (田野), an MS student at Peking University. My research interests mainly focus on AI-Generated Visual Content (AIGC), multi-modal LLM, and unified models. I received my bachelor’s & master’s degree from Peking University, majoring in computer science at the School of Computer Science and Electronic Engineering. I worked closely with Prof. Bin Cui and Ph.D. Ling Yang. I will pursue my Ph.D. at Peking University advised by Prof. Yunhai Tong.

My WeChat account: tyfeld66. Feel free to contact me!

Selected Publications

Training-free Diffusion Acceleration with Bottleneck Sampling
Ye Tian, Xin Xia, Yuxi Ren, Shanchuan Lin, Xing Wang, Xuefeng Xiao, Yunhai Tong, Ling Yang, Bin Cui
[Project Page] [arXiv]

Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening
Ye Tian, Ling Yang, Xinchen Zhang, Yunhai Tong, Mengdi Wang, Bin Cui
[arXiv] [Code]

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
Ling Yang, Xinchen Zhang, Ye Tian, Chenming Shang, Minghao Xu, Wentao Zhang, Bin Cui
[arXiv] [Code]

VideoTetris: VideoTetris: Towards Compositional Text-To-Video Generation
Ye Tian, Ling Yang*, Haotian Yang,Yuan Gao, Yufan Deng, Jingmin Chen, Xintao Wang, Zhaochen Yu, Pengfei Wan,Di Zhang, Bin Cui [Project Page] [arXiv] [Code] NeurIPS, 2024

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
Ling Yang, Ye Tian (equal contribution), Minkai Xu,Zhongyi Liu,Shenda Hong, Wei Qu,Wentao Zhang,Bin Cui,Muhan Zhang, Jure Leskovec [Paper][Code] ICLR, 2024

Internship

• Research Intern at KLing, Kuaishou Technology
• Research Intern at Aisphere, building Pixverse V2.0
• Research Intern at ByteDance. (Present)