Passer au contenu

/ Département d'informatique et de recherche opérationnelle

Je donne

Rechercher

Thèses et mémoires

Des thèses et mémoires de nos étudiants sont conservés et consultables dans Papyrus, le dépôt institutionnel de l'Université de Montréal.

 

 

Pour une recherche détaillée
Visiter Papyrus
Date Trier par date en ordre croissant Titre Trier par titre en ordre croissant
2024 Scalable and robust fog-computing design & dimensioning in dynamic, trustless smart cities
2024 Towards efficient large language models : training low-bitwidth variants and low-rank decomposition of pretrained models
2024 Learning representations for reasoning : generalizing across diverse structures
2024 FACTS-ON : Fighting Against Counterfeit Truths in Online social Networks : fake news, misinformation and disinformation
2024 Aligning language models to code : exploring efficient, temporal, and preference alignment for code generation
2024 Beyond top line metrics : understanding the trade-off between model size and generalization properties
2024 Advancing adversarial robustness with feature desensitization and synthesized data
2024 An investigation of weight perturbation for mitigating Spurious Correlations
2024 Searching for Q*
2023 Emergence of language-like latents in deep neural networks
2023 Multi-task learning for joint diagnosis of CNVs and psychiatric conditions from rs-fMRI
2023 Entanglement-assisted communication complexity and nonlocal games
2023 Domain-specific differencing and merging of models
2023 Remote sensing representation learning for a species distribution modeling case study
2023 Analysis and evaluation of the pilot attentional model
2023 Deep learning algorithms for database-driven peptide search
2023 Detection, recuperation and cross-subject classification of mental fatigue
2023 A multi-agent nudge-based approach for disclosure mitigation online
2023 Predicting stock market trends using time-series classification with dynamic neural networks
2023 Towards an extension of causal discovery with generative flow networks to latent variables models