1

Model Soups Need Only One Ingredient

Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, …

Ke Wang, Yiming Qin, Nikolaos Dimitriadis, Alessandro Favero, Pascal Frossard

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences

Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front …

Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret

Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences

LiNeS: Post-training layer scaling prevents forgetting and enhances model merging

Fine-tuning pre-trained models has become the standard approach to endow them with specialized knowledge, but it poses fundamental …

Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jimenez, Francois Fleuret, Pascal Frossard

LiNeS: Post-training layer scaling prevents forgetting and enhances model merging

Localizing Task Information for Improved Model Merging and Compression

Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez, Francois Fleuret, Pascal Frossard

Pareto Manifold Learning: Tackling Multiple Tasks via Ensembles of Single-Task Models

We present a novel approach to multi-task learning, that utilizes weight ensembles to produce a continuous Pareto Front in a single training run.

Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret

Pareto Manifold Learning: Tackling Multiple Tasks via Ensembles of Single-Task Models

SequeL: A Continual Learning Library in PyTorch and JAX

Nikolaos Dimitriadis, Francois Fleuret, Pascal Frossard

U-Boost NAS: Utilization-boosted Differentiable Neural Architecture Search

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have …

Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard

U-Boost NAS: Utilization-boosted Differentiable Neural Architecture Search

Advances in Morphological Neural Networks: Training, Pruning and Enforcing Shape Constraints

In this paper, we study an emerging class of neural networks, the Morphological Neural networks, from some modern perspectives. Our …

Nikolaos Dimitriadis, Petros Maragos