Homepage

Yuang Ai

Hi, welcome to my website!

I'm Yuang Ai, a third-year Master's student in NLPR-CASIA supervised by Prof. Huaibo Huang and Prof. Ran He.

Before that, I obtained my bachelor degree in electronic information engineering from Beĳing Institute of Technology (GPA:3.9/4.0, Rank:3/397).

My recent research interests primarily focus on topics with significant real-world applications, like efficient visual generative models, unified multi-modal large language models, etc.

I am open to any discussion or collaboration. If you are interested, please feel free to contact me via email.

Email / Google Scholar / Github

Selected Publications

BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Yuang Ai*, Jiaming Han*, Shaobin Zhuang*, Weijia Mao, Xuefeng Hu, Ziyan Yang, Zhenheng Yang, Yali Wang, Huaibo Huang, Xiangyu Yue, and Hao Chen.
Preprint, 2026
paper / code

UniWeTok: An Unified Binary Tokenizer with Codebook Size 2¹²⁸ for Unified Multimodal Large Language Model
Shaobin Zhuang*, Yuang Ai*, Jiaming Han*, Weijia Mao, Xiaohui Li, Fangyikang Wang, Xiao Wang, Yan Li, Shanchuan Lin, Kun Xu, Zhenheng Yang, Huaibo Huang, Xiangyu Yue, Hao Chen, and Yali Wang.
Preprint, 2026
paper / code

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
Yuang Ai, Qihang Fan, Xuefeng Hu, Zhenheng Yang, Ran He, and Huaibo Huang.
NeurIPS Spotlight, 2025
paper / code

DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Yuang Ai, Xiaoqiang Zhou, Huaibo Huang, Xiaotian Han, Zhengyu Chen, Quanzeng You, and Hongxia Yang.
NeurIPS, 2024
paper / code

Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
Yuang Ai, Xiaoqiang Zhou, Huaibo Huang, Lei Zhang, and Ran He.
CVPR, 2024
paper / code

Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration
Yuang Ai, Xiaoqiang Zhou, Huaibo Huang, Jiexiang Wang, and Ran He.
CVPR, 2024
paper / code

Rectifying Magnitude Neglect in Linear Attention
Qihang Fan, Huaibo Huang, Yuang Ai, and Ran He.
ICCV Highlight, 2025
paper / code

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, and Quanzeng You.
EMNLP Findings, 2025
paper / dataset

Internships

ByteDance 2024.03-present, Research intern
Research: Generative models and multi-modal large language models.

OPPO Research Institute 2023.01-2023.03, Research intern
Research: Real-world image super-resolution.

Honours and Awards

2024.12: National scholarship

2024.12: NeurIPS 2024 Top Reviewer (main track)

2023.07: Outstanding Graduate named by Beijing and by BIT

2023.05: Second-Place Winner in the NTIRE 2023 Challenge on Image Super-Resolution

2022.12: Second-Place Winner in the NTIRE 2023 Challenge on 360deg Omnidirectional Image and Video Super-Resolution

2022.12: National scholarship

Academic Service

Reviewer for TPAMI, TIP, CVPR, ICCV, NeurIPS, ICLR, ICML.
Programme Committee for AAAI.

Teaching

Deep Learning Methods and Applications, Teaching Assistant - Fall 2024

Thanks for the source codes from Yang Cao.