Dimitris Samaras

16

Papers

79

Total Citations

Papers (16)

Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers

2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification

∞-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite Dimensions

TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model

GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment

Fast constrained sampling in pre-trained diffusion models

NeurIPS 2025arXiv

Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation

Few-shot Personalized Scanpath Prediction

Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following

AV-Flow: Transforming Text to Audio-Visual Human-like Interactions

Importance-Based Token Merging for Efficient Image and Video Generation

Multi-view Gaze Target Estimation

ZoomLDM: Latent Diffusion Model for Multi-scale Image Generation

SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology

Learned Representation-Guided Diffusion Models for Large-Image Generation