activity
20202023
most citedVISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking

2 citations · 2 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL2023

Probing LLMs for Joint Encoding of Linguistic Categories

Giulio Starace, Konstantinos Papakostas, Rochelle Choenni +4

Large Language Models (LLMs) exhibit impressive performance on a range of NLP tasks, due to the general-purpose linguistic knowledge acquired during pretraining. Existing model int…

cond-mat.mtrl-sci2023

A critical perspective for emerging ultra-thin solar cells with ultra-high power-per-weight outputs

Apostolos Panagiotopoulos, Temur Maksudov, George Kakavelakis +10

Ultrathin, solution-processed emerging solar cells with high power-per-weight (PPW) outputs demonstrate unique potential for applications where low weight, high power output, and f…

cs.CV2023★ 2 cited

VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking

Angelos Nalmpantis, Apostolos Panagiotopoulos, John Gkountouras +2

The lack of interpretability of the Vision Transformer may hinder its use in critical real-world applications despite its effectiveness. To overcome this issue, we propose a post-h…

cs.CV2021

Leveraging Selective Prediction for Reliable Image Geolocation

Apostolos Panagiotopoulos, Giorgos Kordopatis-Zilos, Symeon Papadopoulos

Reliable image geolocation is crucial for several applications, ranging from social media geo-tagging to fake news detection. State-of-the-art geolocation methods surpass human per…

physics.app-ph2020

In-Situ Monitoring of the Charge Carrier Dynamics of CHNHPbI Perovskite Crystallization Process

Efthymis Serpetzoglou, Ioannis Konidakis, Temur Maksudov +3

Although methylammonium lead iodide (CHNHPbI) perovskite has attracted enormous scientific attention over the last decade or so, important information on the charge ext…