activity
20192026
most citedNLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

4 citations · 4 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CV2026

When Negation Is a Geometry Problem in Vision-Language Models

Fawaz Sammani, Tzoulio Chamiti, Paul Gavrikov +1

Joint Vision-Language Embedding models such as CLIP typically fail at understanding negation in text queries, for example, failing to distinguish "no" in the query: "a plain blue s…

cs.CV2025

Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions

Ada Gorgun, Fawaz Sammani, Nikos Deligiannis +2

Diffusion models are usually evaluated by their final outputs, gradually denoising random noise into meaningful images. Yet, generation unfolds along a trajectory, and analyzing th…

cs.CV2025

CLIP-Free, Label Free, Unsupervised Concept Bottleneck Models

Fawaz Sammani, Jonas Fischer, Nikos Deligiannis

Concept Bottleneck Models (CBMs) map dense feature representations into human-interpretable concepts which are then combined linearly to make a prediction. However, modern CBMs rel…

cs.CV2024

Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge

Fawaz Sammani, Nikos Deligiannis

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retriev…

cs.CV20224 cited

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

Fawaz Sammani, Tanmoy Mukherjee, Nikos Deligiannis

Natural language explanation (NLE) models aim at explaining the decision-making process of a black box system via generating natural language sentences which are human-friendly, hi…

cs.CV2020

Show, Edit and Tell: A Framework for Editing Image Captions

Fawaz Sammani, Luke Melas-Kyriazi

Most image captioning frameworks generate captions directly from images, learning a mapping from visual features to natural language. However, editing existing captions can be easi…