2 papers
cs.CV2025
Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural Pruning
Zhaoqi Xu, Yingying Zhang, Jian Li +3
Recent advances in vision-language models (VLMs) have shown remarkable performance across multimodal tasks, yet their ever-growing scale poses severe challenges for deployment and…
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…