4 citations · 5 across the 8 of their papers we have counts for
9 papers
Falcon Perception-HD: High Density Perception via Reinforcement Learning
Sofian Chaybouti, Yasser Dahou, Ngoc Dung Huynh +2
Autoregressive perception models trained to localize visual entities under the open-vocabulary setting are mostly trained using Supervised fine-tuning (SFT) with maximum likelihood…
Falcon Perception
Aviraj Bevli, Sofian Chaybouti, Yasser Dahou +6
Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module…
VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
Brigitta Malagurski Törtei, Yasser Dahou, Ngoc Dung Huynh +5
Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform v…
SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models
Sofian Chaybouti, Sanath Narayan, Yasser Dahou +6
Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such…
REVEAL: Relation-based Video Representation Learning for Video-Question-Answering
Sofian Chaybouti, Walid Bousselham, Moritz Wolter +1
Video-Question-Answering (VideoQA) comprises the capturing of complex visual relation changes over time, remaining a challenge even for advanced Video Language Models (VLM), i.a.,…
MaskInversion: Localized Embeddings via Optimization of Explainability Maps
Walid Bousselham, Sofian Chaybouti, Christian Rupprecht +2
Vision-language foundation models such as CLIP have achieved tremendous results in global vision-language alignment, but still show some limitations in creating representations for…
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
Walid Bousselham, Angie Boggust, Sofian Chaybouti +2
Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However,…
EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System
Sofian Chaybouti, Achraf Saghe, Aymen Shabou
State-of-the-art extractive question-answering models achieve superhuman performances on the SQuAD benchmark. Yet, they are unreasonably heavy and need expensive GPU computing to a…
MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
Sofian Chaybouti, Achraf Saghe, Aymen Shabou
This paper introduces MIX, a multi-task deep learning approach to solve open-ended question-answering. First, we design our system as a multi-stage pipeline of 3 building blocks: a…