3 papers
cs.LG2026
Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
Kevin Wang, Hongqian Niu, Didong Li
As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degradation or collapse. In this article,…
cs.CV2025
Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
Dharsan Ravindran, Kevin Wang, Zhuoyuan Cao +2
Recent advances in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have achieved state-of-the-art performance on general image segmentati…
cs.LG2025
Deep Generative Models: Complexity, Dimensionality, and Approximation
Kevin Wang, Hongqian Niu, Yixin Wang +1
Generative networks have shown remarkable success in learning complex data distributions, particularly in generating high-dimensional data from lower-dimensional inputs. While this…