Biography
I am currently a Senior Research Scientist at Alibaba, focusing on large language models, multimodal models, and their applications in search ads, under the leadership of Jian Xu. Previously, I was a researcher at SenseTime, where I worked on computer vision and neural architecture search with Ming Sun, Prof. Wanli Ouyang, and Dr. Junjie Yan. Prior to that, I researched object detection and segmentation at Baidu’s Institute of Deep Learning (IDL) under Shilei Wen.
I earned my master’s degree from the School of Computer Science at Beijing Institute of Technology, supervised by Prof. Yuwei Wu and Prof. Yunde Jia.
If you are interested in working with me as a research intern, please feel free to drop me an email through xingyuanbu at gmail dot com.
General information
-
Links:
Google Scholar 
GitHub 
LinkedIn - Email: xingyuanbu at gmail dot com
- Research interests: Computer Vision, Multimodality, Large Language Models.
- Professional Services: I am a reviewer for several top-tier conferences and journals, ICLR, NeurIPS, CVPR, ACL, EMNLP, NAACL, MM, TPAMI, TCSVT, TMM, CVIU, PR.
Selected Publications
*Equal contribution, #Corresponding author
- GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models. Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu*#, Ge Bai et al. EMNLP 2024. [paper]
- MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues. Ge Bai, Jie Liu, Xingyuan Bu*#, Yancheng He, Jiaheng Liu et al. ACL 2024. [paper] [code]
- ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models. Yanan Wu, Jie Liu, Xingyuan Bu*, Jiaheng Liu et al. ACL 2024. [paper] [code]
- Large-Scale Object Detection in the Wild With Imbalanced Data Distribution, and Multi-Labels. Cong Pan, Junran Peng, Xingyuan Bu, and Zhaoxiang Zhang. TPAMI 2024. [paper]
- RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts. Jiaheng Liu, Zehao Ni, Haoran Que,.. Xingyuan Bu et al. NeurIPS 2024. [paper]
- GAIA-Universe: Everything is Super-Netify. Junran Peng, Qing Chang, Haoran Yin, Xingyuan Bu, Jiajun Sun, Lingxi Xie, Xiaopeng Zhang, Qi Tian, and Zhaoxiang Zhang. TPAMI 2023. [paper] [code]
- Visual Encoding and Debiasing for CTR Prediction. Guipeng Xv, Si Chen, Chen Lin, Wanxian Guan, Xingyuan Bu, Xubin Li, Hongbo Deng, Jian Xu et al. CIKM 2022. [paper]
- GAIA: A Transfer Learning System of Object Detection that Fits Your Needs. Xingyuan Bu, Junran Peng, Junjie Yan, Tieniu Tan, and Zhaoxiang Zhang. CVPR 2021. [paper] [code]
- Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels. Junran Peng, Xingyuan Bu*, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, and Junjie Yan. CVPR 2020. [paper]
- Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds. Zhi Gao, Yuwei Wu, Xingyuan Bu, Tan Yu, Junsong Yuan, and Yunde Jia. Pattern Recognition 2019. [paper]
- Deep Convolutional Network with Locality and Sparsity Constraints for Texture Classification. Xingyuan Bu, Yuwei Wu, Zhi Gao, and Yunde Jia. Pattern Recognition 2019. [paper]