About

I am a Chief AIGC Scientist at Intellifusion Inc., working on Transformer optimization, generative AI (text-to-image, text-to-video, text-to-3D), and multimodal large language models (MLLM).

Education

Beijing University of Posts and Telecommunications (BUPT) 2008 – 2015
Ph.D. — Signal and Information Processing
Beijing University of Posts and Telecommunications (BUPT) 2004 – 2008
B.S. — Information Engineering

Work Experience

Intellifusion Inc. Mar 2024 – Present
Chief AIGC Scientist
Transformer optimization, AIGC (T2I, T2V, Text-to-3D), MLLM
International Digital Economy Academy (IDEA) Aug 2021 – Mar 2024
Senior Researcher
AIGC, model optimization, LLM, object detection
Ping An Property Insurance Apr 2019 – Jul 2021
Senior Image Expert (Team Manager)
Object detection and recognition, OCR, NLP
Shenzhen Research Institute of Big Data (SRIBD) May 2018 – Apr 2019
Research Scientist
Object detection and recognition, OCR
Hong Kong Polytechnic University (HK PolyU) May 2016 – May 2018
Postdoctoral Researcher
Deep learning for facial attribute analysis
University of Oulu, Center for Machine Vision Research Jan 2014 – Nov 2015
Researcher / Postdoctoral Researcher
Texture analysis, medical image processing

Teaching & Outreach

Mathematics of Deep Learning — Linear Algebra, Vector Calculus, Convex Optimization (Nesterov), Deep Learning Concepts
Mathematics of Transformer — Numerical Linear Algebra, Matrix Calculus, High-dimensional Probability, Transformer
Mathematics of Machine Learning — Numerical Linear Algebra, Matrix / Vector Calculus, Probability, Numerical Optimization
Generative AI (AIGC) — Variational AutoEncoder, Normalizing Flow, Diffusion Model, Auto-regressive Methods, Energy-based Methods

Mathematics of Deep Learning — 268,000+ views

Mathematics of Transformer — 77,000+ views

Selected Publications

* denotes corresponding author or project leader. Full list on Google Scholar →

1. Optimization of Deep Learning & LLM

DNT: A Deeply Normalized Transformer That Can Be Trained by Momentum SGD
Xianbiao Qi*, Marco Chen, Wenjie Xiao, Jiaquan Ye, Yelin He, Chun-Guang Li, Zhouchen Lin
ICLR 2026
Taming Transformer Without Using Learning Rate Warmup
Xianbiao Qi*, Yelin He, Jiaquan Ye, Chun-Guang Li, Bojia Zi, Xili Dai, Qin Zou, Rong Xiao
ICLR 2025
LipsFormer: Introducing Lipschitz Continuity to Vision Transformers
Xianbiao Qi*, Jianan Wang, Yihao Chen, Yukai Shi, Lei Zhang
ICLR 2023
SimpleGPT: Improving GPT via a Simple Normalization Strategy
Xianbiao Qi*, Marco Chen, Yelin He, Jiaquan Ye, Rong Xiao
Submission ICML 2026
Delving into Muon and Beyond: Deep Analysis and Extensions
Xianbiao Qi*, Marco Chen, Yelin He, Jiaquan Ye, Rong Xiao
Submission ICML 2026

2. AIGC (Image / Video / 3D Generation)

Refaçade: Editing Object with Given Reference Texture
Youze Huang, Penghui Ruan, Bojia Zi, Xianbiao Qi*, Jianan Wang, Rong Xiao
CVPR 2026
CTRL&SHIFT: High-quality Geometry-Aware Object Manipulation in Visual Generation
Penghui Ruan, Bojia Zi, Xianbiao Qi*, et al.
ICLR 2026
Senorita-2M: A High-Quality Instruction-based Dataset for General Video Editing
Bojia Zi, Penghui Ruan, Marco Chen, Xianbiao Qi*, et al.
NeurIPS 2025
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
Bojia Zi, Weixuan Peng, Xianbiao Qi*, Jianan Wang, Shihao Zhao, Rong Xiao, Kam-Fai Wong
NeurIPS 2025
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation
Shaozhe Hao, Xuantong Liu, Xianbiao Qi*, Shihao Zhao, Bojia Zi, Rong Xiao, Kai Han, Kwan-Yee K. Wong
ICLR 2025
Elucidating the Design Space of Language Models for Image Generation
Xuantong Liu, Shaozhe Hao, Xianbiao Qi*, Tianyang Hu, Jun Wang, Rong Xiao, Yuan Yao
ICML 2025
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
Bojia Zi, Shihao Zhao, Xianbiao Qi*, et al.
AAAI 2025
DreamTime: An Improved Optimization Strategy for Text-to-3D Content Creation
Yukun Huang, Jianan Wang, Yukai Shi, Xianbiao Qi, Zheng-Jun Zha, Lei Zhang
ICLR 2024
TOSS: High-quality Text-guided Novel View Synthesis from a Single Image
Yukai Shi, Jianan Wang, He Cao, Boshi Tang, Xianbiao Qi, et al.
ICLR 2024
DreamWaltz: Make a Scene with Complex 3D Animatable Avatars
Yukun Huang, Jianan Wang, Ailing Zeng, He Cao, Xianbiao Qi, Yukai Shi, Zheng-Jun Zha, Lei Zhang
NeurIPS 2023

3. General Computer Vision

DAB-DETR: Dynamic Anchor Boxes Are Better Queries for DETR
Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, Lei Zhang
ICLR 2022
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection
Qin Zou, Zheng Zhang, Qingquan Li, Xianbiao Qi, Qian Wang, Song Wang
IEEE TIP 2018

4. OCR & Document Understanding

MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
Ning Lu, Wenwen Yu, Xianbiao Qi*, Yihao Chen, Ping Gong, Rong Xiao, Xiang Bai
Pattern Recognition 2021
PICK: Processing Key Information Extraction from Documents Using Improved Graph Learning
Wenwen Yu, Ning Lu, Xianbiao Qi*, Ping Gong, Rong Xiao
ICPR 2021
EMU: Effective Multi-Hot Encoding for Lightweight Scene Text Recognition
Bingcong Li, Xin Tang, Xianbiao Qi*, Yihao Chen, Chun-Guang Li, Rong Xiao
IEEE TCSVT 2022

5. LLM & MLLM

DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
Yihao Chen, Xianbiao Qi*, Jianan Wang, Lei Zhang
CVPR 2023
Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices
Bojia Zi, Xianbiao Qi*, Lingzhi Wang, Jianan Wang, Kam-Fai Wong, Lei Zhang
arXiv 2023
Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery
Wei He, Xianghan Meng, Zhiyuan Huang, Xianbiao Qi, Rong Xiao, Chun-Guang Li
CVPR 2026

Honors & Awards

ICDAR 2021 Table Recognition to LaTeX — Champion
ICDAR 2021 Formula Detection Competition — Champion
CVPR 2021 TextVQA Competition — Champion
ICDAR 2019 Receipt Recognition Key Information Extraction — Champion
Pattern Recognition Letters Special Issue — Fluorescence Cell Recognition — Champion & Runner-up
ICDAR 2021 Table Recognition to HTML — Runner-up
Baidu / Peking University Global Autonomous Driving Competition — Runner-up
5th China Innovation Challenge Smart Education Special Competition — Runner-up
Ping An Group Young Scientist (9 selected among 400,000+ employees)
Ping An Group Breakthrough Innovation Award
2022 MIIT "揭榜挂帅" Project — Successfully Shortlisted Unit (third applicant)
ICLR 2026 Area Chair  |  CVPR 2021 Outstanding Reviewer
Work reported by CCTV Finance Channel and CCTV News Channel