publications

2026

1. ICLR

   

   Massive Editing for Large Language Models Based on Dynamic Weight Generation.

   Wentao Wan^*, Qiqing Lao^*, Zhiwei Xie^*, and 4 more authors

   In Proceeding of the International Conference on Learning Representations (ICLR), 2026

   PDF Code
2. TMM

   

   Towards top-down reasoning: An explainable multi-agent approach for visual question answering.

   Zeqing Wang, Wentao Wan, Qiqing Lao, and 6 more authors

   IEEE Transactions on Multimedia (TMM), 2026

   Project Lead: Initiated the research topic, proposed the core methodology, and mentored the 1st author during project execution and manuscript writing.

   PDF Code
3. AAAI

   

   ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation.

   Zhuojie Yang^*, Wentao Wan^*, and Keze Wang

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026

   Project Lead: Initiated the research topic, co-designed the technical framework, and mentored the 1st author during project execution and manuscript writing.

   PDF Code

2025

1. Preprint

   

   Enhancing Visual Programming for Visual Reasoning via Probabilistic Graphs.

   Wentao Wan, Kaiyu Wu, Qingyang Ma, and 4 more authors

   arXiv preprint arXiv:2512.14257, 2025

   PDF
2. Preprint

   

   A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks.

   Wentao Wan^*, Nan Kang^*, Zhuojie Yang, and 3 more authors

   arXiv preprint arXiv:2309.09809, 2025

   PDF
3. CVPR

   

   Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body.

   Zeqing Wang, Qingyang Ma, Wentao Wan, and 3 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Highlight, 2025

   Project Lead: Proposed the core methodology and elevated the research vision beyond standard cross-modal alignment. Mentored the 1st and 2nd authors during project execution and manuscript writing.

   PDF Code
4. AAAI

   

   SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks.

   Wentao Wan, Zhuojie Yang, Yongcan Chen, and 6 more authors

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025

   PDF Code

2023

1. PRCV

   

   Interactive Learning for Interpretable Visual Recognition via Semantic-Aware Self-Teaching Framework.

   Hao Jiang, Haowei Li, Junhao Chen, and 2 more authors

   In Proceedings of the Conference on Pattern Recognition and Computer Vision (PRCV), 2023

   PDF

2021

1. ICCV

   

   Linguistically Routing Capsule Network for Out-of-distribution Visual Question Answering.

   Qingxing Cao, Wentao Wan, Keze Wang, and 2 more authors

   In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021

   PDF

2018

1. PCM

   

   CS-DeCNN: Deconvolutional Neural Network for Reconstructing Images from Compressively Sensed Measurements.

   Wentao Wan, Guohui Li, and Peng Pan

   In Proceedings of the Pacific-Rim Conference on Multimedia (PCM), 2018

   Note: The PCM conference was later upgraded and merged to become ACM Multimedia Asia (ACM MM Asia).

   PDF