Scholar
Bowen Qu
Google Scholar ID: m8ttvBkAAAAJ
Peking University, Ex: Rhymes.ai Aria Team
Citations & Impact
Citations
541
H-index
9
i10-index
9
Publications
12
Co-authors
6
list available
Publications
Cited
0
Resume (English only)
Academic Achievements
- Publications:
- - 'ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding', ICLR2025 Oral (1.8%).
- - 'Aria: An Open Multimodal Native Mixture-of-Experts Model', Technical Report.
- - 'Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap', CVPRW2024.
- - 'Bringing Textual Prompt to AI-Generated Image Quality Assessment', ICME2024.
- Projects Released:
- - 2025.02: ChartMoE selected as ICLR2025 Oral.
- - 2025.01: ChartMoE accepted by ICLR2025.
- - 2024.10: Released Aria, a native LMM excelling in text, code, image, video, PDF, and more.
- - 2024.09: Released ChartMoE, an MLLM with MoE connector for advanced chart understanding, replot, editing, highlighting, and transformation.
Research Experience
- Participated in several interesting MLLM research projects:
- - 2024.05 - 2024.12: 01.ai & Rhymes.ai, Multimodal Team, supervised by Junnan Li, working closely with Dongxu Li and Haoning Wu.
- - 2024.02 - 2024.07: IDEA Research, working closely with Zhengzhuo Xu, Yiyan Qi, and Chengjin Xu.
Education
- An MPhil. Candidate at the School of Electronic and Computer Science (SECE), Peking University (PKU) since 2022 fall; previously received an Honours B.E. degree from the School of Electronic Information and Communications (EIC), Huazhong University of Science and Technology (HUST) in June 2022.
Background
- Research interests include Vision-Language Model and MLLM Reasoning.
Miscellany
- Enjoys open-sourcing. The logo of his website is his pet cat, Baka.
