Research

Research Overview

My research focuses on AI for AI (AI4AI), world models, and learning theory - building learning systems that can design, improve, and understand themselves, while remaining grounded in statistical and structural principles.

Current Interests

• AI4AI

• World models

• Learning theory

Selected Publications

(Equal contribution and corresponding authorship are noted inline.)

AI4AI

1. Zhen Liu, Yuhan Liu, Jinjun Wang, Wei Song, Jianyi Liu, Jingwen Fu (corresponding). Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search. International Conference on Machine Learning (ICML), 2026.

2. Zhen Liu, Wanqi Zhou, Shuanghao Bai, Wei Song, He Zhang, Yuhan Liu, Jingwen Fu (corresponding). Accelerating Neural Architecture Search with Code Semantics. EMNLP, 2026.

3. Jingwen Fu, Zhen Liu, Yuhan Liu, He Zhang, Nanning Zheng. Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination. arXiv:2607.28947, 2026.

Learning Theory

1. Jingwen Fu, Nanning Zheng. On the Statistic Properties of the Distributional Compositional Generalization. International Conference on Machine Learning (ICML), 2025.

2. Jingwen Fu, Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng. Breaking Through the Learning Plateaus of In-context Learning in Transformer. International Conference on Machine Learning (ICML), 2024.

3. Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen. Closing the Gap Between the Upper Bound and Lower Bound of Adam's Iteration Complexity. Advances in Neural Information Processing Systems (NeurIPS), 2023. (equal contribution)

4. Jingwen Fu, Zhizheng Zhang, Dacheng Yin, Yan Lu, Nanning Zheng. Learning Trajectories are Generalization Indicators. Advances in Neural Information Processing Systems (NeurIPS), 2023.

5. Meidai Xuanyuan, Tao Yang, Jingwen Fu, Yuwang Wang. Insufficient Task Description can Impair In-context Learning: A Study from Information Perspective. Information Fusion, 2025.

Multimodal Perception

1. Yuhan Liu, Jingwen Fu, Yang Wu, Kangyi Wu, Pengna Li, Jiayi Wu, Sanping Zhou, Jingmin Xin. Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching. International Conference on Computer Vision (ICCV), 2025.

2. Yanqing Shen, Sanping Zhou, Jingwen Fu, Ruotong Wang, Shitao Chen, Nanning Zheng. StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.

3. Kangyi Wu, Pengna Li, Jingwen Fu, Yizhe Li, Yang Wu, Yuhan Liu, Jinjun Wang, Sanping Zhou. Event-Equalized Dense Video Captioning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

4. Pengna Li, Kangyi Wu, Jingwen Fu, Sanping Zhou. REGNav: Room Expert Guided Image-Goal Navigation. AAAI Conference on Artificial Intelligence (AAAI), 2025.

5. Yanqing Shen, Sanping Zhou, Jingwen Fu, Ruotong Wang, Shitao Chen, Nanning Zheng. StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

6. Jingwen Fu, Xiaoyi Zhang, Yuwang Wang, Wenjun Zeng, Nanning Zheng. Understanding Mobile GUI: from Pixel-Words to Screen-Sentences. Neurocomputing, 2024. (equal contribution)

A fuller list of papers and citations is on Google Scholar.