3 papers
cs.AI2026
Geo-Code: A Code Framework for Reverse Code Generation from Geometric Images Based on Two-Stage Multi-Agent Evolution
Zhenyu Wu, Yanxi Long, Jian Li +1
Program code serves as a bridge linking vision and logic, providing a feasible supervisory approach for enhancing the multimodal reasoning capability of large models through geomet…
cs.AI2025
MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question Generation
Zhenyu Wu, Jian Li, Hua Huang
Educational illustrations play a central role in communicating abstract concepts, yet current multimodal large language models (MLLMs) remain limited in producing pedagogically coh…
cs.LG2025
Understanding Generalization in Transformers: Error Bounds and Training Dynamics Under Benign and Harmful Overfitting
Yingying Zhang, Zhenyu Wu, Jian Li +1
Transformers serve as the foundational architecture for many successful large-scale models, demonstrating the ability to overfit the training data while maintaining strong generali…