599 citations · 1.2k across the 114 of their papers we have counts for
135 papers
Latent Flow Matching for Molecular Graph Generation
Mathis Goupillon, Roman Bresson, Konstantinos Divriotis +1
Modern graph generative models typically operate directly in the discrete graph space, explicitly generating node and edge variables, which can become costly as graphs grow. In thi…
Refining Heuristic-Based Bitcoin Address Clustering with Graph Neural Networks
Hugo Schnoering, Roman Bresson, Michalis Vazirgiannis
Bitcoin's pseudonymous nature makes it challenging to analyze user-level activity, since a single user may control multiple identifiers (addresses). Existing heuristic-based method…
Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks
Xiao Fei, Yang Zhang, Sarah Almeida Carneiro +1
Most multiple-choice question (MCQ) benchmarks evaluate Large Language Models (LLMs) only by whether they select the correct answers. This binary scoring treats all incorrect respo…
Jais 2: A Family of Arabic-Centric Open Large Language Models
Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim +57
Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong p…
The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs
Yang Zhang, Xiao Fei, Amr Mohamed +6
Large language models are increasingly used to answer culturally grounded questions across languages, yet it remains unclear whether local cultural knowledge is better accessed thr…
CARTE: A Benchmark for Mapping Language Model Knowledge Across France
Sarah Almeida Carneiro, Christos Xypolopoulos, Xiao Fei +2
We introduce CARTE (Culturally Anchored Regional-Territorial Evaluation), a multiple-choice benchmark for evaluating the ability of large language models (LLMs) to discriminate fin…
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
Roman Bresson, Konstantinos Divriotis, Johannes F. Lutzeyer +2
We introduce GraViti, a transformer-based graph-level variational autoencoder that encodes entire graphs into single, fixed-dimensional latent vectors rather than per-node embeddin…
PPI2Text: Captioning Protein-Protein Interactions with Coordinate-Aligned Pair-Map Decoding
Xiao Fei, Sarah Almeida Carneiro, Yang Zhang +4
Protein-protein interaction (PPI) modeling has been widely studied as a binary or multi-label classification task. While emerging multimodal large language models (LLMs) can now de…
GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek
Yang Zhang, Mersin Konomi, Christos Xypolopoulos +6
Large Language Models (LLMs) are commonly trained on multilingual corpora that include Greek, yet reliable evaluation benchmarks for Greek-particularly those based on authentic, na…
Markovian Generation Chains in Large Language Models
Mingmeng Geng, Amr Mohamed, Guokan Shang +2
The widespread use of large language models (LLMs) raises an important question: how do texts evolve when they are repeatedly processed by LLMs? In this paper, we define this itera…
A Kinetic Energy Perspective of Flow Matching
Ziyun Li, Huancheng Hu, Soon Hoe Lim +6
Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corres…
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Abdelaziz Bounhar, Rania Hossam Elmohamady Elbadry, Hadi Abdine +3
Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-…
A Greek Government Decisions Dataset for Public-Sector Analysis and Insight
Giorgos Antoniou, Giorgos Filandrianos, Aggelos Vlachos +4
We introduce an open, machine-readable corpus of Greek government decisions sourced from the national transparency platform Diavgeia. The resource comprises 1 million decisions, fe…
Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules
Amr Mohamed, Yang Zhang, Michalis Vazirgiannis +1
Diffusion large language models (dLLMs) offer a promising alternative to autoregressive models, but their practical utility is severely hampered by slow, iterative sampling. We pre…
Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
Abdelaziz Bounhar, Hadi Abdine, Evan Dufraisse +5
Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (R…
If You Want to Be Robust, Be Wary of Initialization
Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis +1
Graph Neural Networks (GNNs) have demonstrated remarkable performance across a spectrum of graph-related tasks, however concerns persist regarding their vulnerability to adversaria…
Cell2Text: Multimodal LLM for Generating Single-Cell Descriptions from RNA-Seq Data
Oussama Kharouiche, Aris Markogiannakis, Xiao Fei +2
Single-cell RNA sequencing has transformed biology by enabling the measurement of gene expression at cellular resolution, providing information for cell types, states, and disease…
ADMP-GNN: Adaptive Depth Message Passing GNN
Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer +1
Graph Neural Networks (GNNs) have proven to be highly effective in various graph learning tasks. A key characteristic of GNNs is their use of a fixed number of message-passing step…
Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts
Guokan Shang, Hadi Abdine, Ahmad Chamma +7
We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts…
Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text
Amr Mohamed, Yang Zhang, Michalis Vazirgiannis +1
Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities, and increasingly…
Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning
Yang Zhang, Amr Mohamed, Hadi Abdine +2
Curriculum learning-organizing training data from easy to hard-has improved efficiency across machine learning domains, yet remains underexplored for language model pretraining. We…
Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
Xiao Fei, Michail Chatzianastasis, Sarah Almeida Carneiro +3
Predicting protein function from sequence is a central challenge in computational biology. While existing methods rely heavily on structured ontologies or similarity-based techniqu…
Prediction via Shapley Value Regression
Amr Alkhatib, Roman Bresson, Henrik Boström +1
Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, lea…
Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation
Ashraf Ghiye, Baptiste Barreau, Laurent Carlier +1
Graph Neural Networks have significantly advanced research in recommender systems over the past few years. These methods typically capture global interests using aggregated past in…