activity
20242026
collaborators

7 papers

cs.LG2026

Nectar: Neural Estimation of Cached-Token Attention via Regression

João Monteiro, Michal Klein, Pierre Ablin +1

Evaluating softmax attention over a fixed long context requires reading every cached key-value pair for each new query token. For a given context (a book, a manual, a legal corpus)…

cs.CL2026

LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss

Szilvia Ujváry, Louis Béthune, Pierre Ablin +3

Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their paramet…

cs.LG2026

DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures

Eleonora Gualdoni, Sonia Laguna, Louis Bethune +3

Multi-domain fine-tuning of large language models requires improving performance on target domains while preserving performance on constrained domains, such as general knowledge, i…

cs.LG2026

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

Hao Xu, Xiangru Jian, Xinjian Zhao +9

This paper introduces GraphOmni, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs on graph-theoretic tasks articulated in natural language. GraphOm…

cs.CL2026

MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings

Andrea Gurioli, Federico Pennino, João Monteiro +1

Deploying language models often requires navigating accuracy vs. performance trade-offs to meet latency constraints while preserving utility. Traditional model distillation reduces…

cs.CL2025

Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy

Saeid Asgari Taghanaki, Joao Monteiro

Large language models (LLMs) have demonstrated remarkable proficiency in generating detailed and coherent explanations of complex concepts. However, the extent to which these model…