Qian Ma

My current research focuses on multimodal learning and reasoning, vision-language models (VLMs), multimodal RAG, knowledge-based visual question answering (KB-VQA), and reliable foundation-model evaluation.

I am interested in how foundation models ground non-textual structure, visual entities, and external knowledge. Before moving toward multimodal RAG and KB-VQA, I worked on graph learning, graph self-supervised learning, graph foundation models, spatio-temporal forecasting, time-series modeling, and urban computing.

1. Qian Ma, S M Rayeed, Charles V. Stewart, Qiong Wu, Yao Ma. Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting. ECCV 2026, to appear.
2. Qian Ma, Qiong Wu, Zhengyi Zhou, Yao Ma. Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification. ACL 2026 Findings, to appear.
3. Qian Ma, Haitao Mao, Jingzhe Liu, Zhehua Zhang, Chunlin Feng, Yu Song, Yihan Shao, Yao Ma. Do Neural Scaling Laws Exist on Graph Self-Supervised Learning? LoG 2024.
4. Qian Ma, Hongliang Chi, Hengrui Zhang, Kay Liu, Zhiwei Zhang, Lu Cheng, Suhang Wang, Philip S. Yu, Yao Ma. Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarks. ACM SIGKDD Explorations, 2025.
5. Qian Ma, Haitao Mao, Zhehua Zhang, Qiong Wu, Zhengyi Zhou, Yao Ma. Cross-Domain GraphWalker: Harnessing LLMs for Graph Structure Learning. Under review.
6. Qian Ma, Zijian Zhang, Xiangyu Zhao, Haoliang Li, Hongwei Zhao, Yiqi Wang, Zitao Liu, Wanyu Wang. Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting. CIKM 2023.
7. Zijian Zhang, Xiangyu Zhao, Qidong Liu, Chunxu Zhang, Qian Ma, et al. PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction. CIKM 2023.

See my Google Scholar profile for updates.