7 papers
ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs
Mohamed Amine Kerkouri, Simon D. Hernandez, Marouane Tliba +3
We present ThinkProbe, a framework for structural analysis of LLM reasoning traces. ThinkProbe converts each trace into a Thought Graph a directed graph with cycles, 8 node types,…
What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metric
Mohamed Amine Kerkouri, Marouane Tliba, Bin Wang +3
Scanpath similarity metrics are central to eye-movement research, yet existing methods predominantly evaluate spatial and temporal alignment while neglecting semantic equivalence b…
SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani +1
Understanding human visual attention is key to preserving cultural heritage We introduce SPGen a novel deep learning model to predict scanpaths the sequence of eye movementswhen vi…
Morphology-Aware KOA Classification: Integrating Graph Priors with Vision Models
Marouane Tliba, Mohamed Amine Kerkouri, Yassine Nasser +4
Knee osteoarthritis (KOA) diagnosis from radiographs remains challenging due to the subtle morphological details that standard deep learning models struggle to capture effectively.…
Modeling Beyond MOS: Quality Assessment Models Must Integrate Context, Reasoning, and Multimodality
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani +2
This position paper argues that Mean Opinion Score (MOS), while historically foundational, is no longer sufficient as the sole supervisory signal for multimedia quality assessment…
Shifts in Doctors' Eye Movements Between Real and AI-Generated Medical Images
David C Wong, Bin Wang, Gorkem Durak +21
Eye-tracking analysis plays a vital role in medical imaging, providing key insights into how radiologists visually interpret and diagnose clinical cases. In this work, we first ana…