Ioannis (Giannis) Maniadis

Ioannis (Giannis) Maniadis

Research Scientist @ Samsung AI Center - Cambridge

I am Research Scientist at the Future Interaction group in Samsung’s AI Center - Cambridge since 2024. Earlier, I completed my PhD at Queen Mary University of London in the MMV Group, supervised by Prof. Ioannis Patras and Prof. Georgios Tzimiropoulos. My research interests revolve around representation learning for vision & language models.

Selected Publications

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

Ioannis Maniadis Metaxas, Adrian Bulat, Alberto Baldrati, Anestis Zaganidis, Yassine Ouali, Hyeonuk Kim, Georgios Tzimiropoulos

European Conference on Computer Vision (ECCV) 2026

Arxiv   Citation  
VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions

Adrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas, Yassine Ouali, Georgios Tzimiropoulos

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

Arxiv   Citation  
Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing

Ioannis Maniadis Metaxas, Georgios Tzimiropoulos, Ioannis Patras

European Conference on Computer Vision (ECCV) 2024

Arxiv   Code   Citation  
Aligned Unsupervised Pretraining of Object Detectors with Self-training

Ioannis Maniadis Metaxas, Adrian Bulat, Ioannis Patras, Brais Martinez, Georgios Tzimiropoulos

Preprint

Arxiv   Citation  
DivClust: Controlling Diversity in Deep Clustering

Ioannis Maniadis Metaxas, Georgios Tzimiropoulos, Ioannis Patras

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Arxiv   Code   Citation