Picture for Marius Leordeanu

Marius Leordeanu

Institute of Mathematics of the Romanian Academy, University "Politehnica" of Bucharest

Closer to Ground Truth: Realistic Shape and Appearance Labeled Data Generation for Unsupervised Underwater Image Segmentation

Add code
Mar 20, 2025
Viaarxiv icon

A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction

Add code
Mar 05, 2025
Viaarxiv icon

Towards Zero-Shot & Explainable Video Description by Reasoning over Graphs of Events in Space and Time

Add code
Jan 14, 2025
Viaarxiv icon

Label up: Learning Pulmonary Embolism Segmentation from Image Level Annotation through Model Explainability

Add code
Dec 10, 2024
Figure 1 for Label up: Learning Pulmonary Embolism Segmentation from Image Level Annotation through Model Explainability
Figure 2 for Label up: Learning Pulmonary Embolism Segmentation from Image Level Annotation through Model Explainability
Figure 3 for Label up: Learning Pulmonary Embolism Segmentation from Image Level Annotation through Model Explainability
Figure 4 for Label up: Learning Pulmonary Embolism Segmentation from Image Level Annotation through Model Explainability
Viaarxiv icon

"Vorbeşti Româneşte?" A Recipe to Train Powerful Romanian LLMs with English Instructions

Add code
Jun 26, 2024
Viaarxiv icon

OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs

Add code
May 17, 2024
Figure 1 for OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
Figure 2 for OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
Figure 3 for OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
Figure 4 for OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
Viaarxiv icon

Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning

Add code
Feb 12, 2024
Figure 1 for Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning
Figure 2 for Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning
Figure 3 for Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning
Figure 4 for Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning
Viaarxiv icon

Maia: A Real-time Non-Verbal Chat for Human-AI Interaction

Add code
Feb 09, 2024
Figure 1 for Maia: A Real-time Non-Verbal Chat for Human-AI Interaction
Figure 2 for Maia: A Real-time Non-Verbal Chat for Human-AI Interaction
Figure 3 for Maia: A Real-time Non-Verbal Chat for Human-AI Interaction
Figure 4 for Maia: A Real-time Non-Verbal Chat for Human-AI Interaction
Viaarxiv icon

Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations

Add code
Aug 21, 2023
Figure 1 for Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations
Figure 2 for Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations
Figure 3 for Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations
Figure 4 for Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations
Viaarxiv icon

Self-supervised Hypergraphs for Learning Multiple World Interpretations

Add code
Aug 21, 2023
Viaarxiv icon