← Search

Nhat Hoang-Xuan

2 accepted papers

2025

Advancing Interpretability of CLIP Representations with Concept Surrogate Model

NeurIPS 2025poster

Contrastive Language-Image Pre-training (CLIP) generates versatile multimodal embeddings for diverse applications, yet the specific information captured within these representations is not fully understood. Current explainability techniques often target specific tasks, overlooking the rich, general…

Cited by 0SourceScholar
2025

NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions

ICLR 2025poster

Understanding the inner workings of neural networks is essential for enhancing model performance and interpretability. Current research predominantly focuses on examining the connection between individual neurons and the model's final predictions, which suffers from challenges in interpreting the in…