Nicolaou, Mihalis

4 publications

NeurIPS 2025 Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders James Oldfield, Shawn Im, Sharon Li, Mihalis Nicolaou, Ioannis Patras, Grigorios Chrysos

ICML 2024 Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses Panagiotis Koromilas, Giorgos Bouritsas, Theodoros Giannakopoulos, Mihalis Nicolaou, Yannis Panagakis

ICLR 2023 PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis Nicolaou, Ioannis Patras

NeurIPS 2023 Parts of Speech–Grounded Subspaces in Vision-Language Models James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis Nicolaou, Ioannis Patras