Picture for Ismini Lourentzou

Ismini Lourentzou

Uncertainty in Action: Confidence Elicitation in Embodied Agents

Add code
Mar 13, 2025
Viaarxiv icon

FAIR: Facilitating Artificial Intelligence Resilience in Manufacturing Industrial Internet

Add code
Mar 03, 2025
Viaarxiv icon

CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models

Add code
Dec 26, 2024
Viaarxiv icon

PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation

Add code
Dec 19, 2024
Figure 1 for PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
Figure 2 for PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
Figure 3 for PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
Figure 4 for PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
Viaarxiv icon

Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG

Add code
Dec 12, 2024
Viaarxiv icon

uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures

Add code
Mar 14, 2024
Viaarxiv icon

Commonsense for Zero-Shot Natural Language Video Localization

Add code
Dec 29, 2023
Figure 1 for Commonsense for Zero-Shot Natural Language Video Localization
Figure 2 for Commonsense for Zero-Shot Natural Language Video Localization
Figure 3 for Commonsense for Zero-Shot Natural Language Video Localization
Figure 4 for Commonsense for Zero-Shot Natural Language Video Localization
Viaarxiv icon

Sedition Hunters: A Quantitative Study of the Crowdsourced Investigation into the 2021 U.S. Capitol Attack

Add code
Feb 21, 2023
Figure 1 for Sedition Hunters: A Quantitative Study of the Crowdsourced Investigation into the 2021 U.S. Capitol Attack
Figure 2 for Sedition Hunters: A Quantitative Study of the Crowdsourced Investigation into the 2021 U.S. Capitol Attack
Figure 3 for Sedition Hunters: A Quantitative Study of the Crowdsourced Investigation into the 2021 U.S. Capitol Attack
Figure 4 for Sedition Hunters: A Quantitative Study of the Crowdsourced Investigation into the 2021 U.S. Capitol Attack
Viaarxiv icon

Learning by Asking for Embodied Visual Navigation and Task Completion

Add code
Feb 09, 2023
Viaarxiv icon

Rationalization for Explainable NLP: A Survey

Add code
Jan 21, 2023
Figure 1 for Rationalization for Explainable NLP: A Survey
Figure 2 for Rationalization for Explainable NLP: A Survey
Figure 3 for Rationalization for Explainable NLP: A Survey
Figure 4 for Rationalization for Explainable NLP: A Survey
Viaarxiv icon