Nikolaos Dimitriadis

5 papers · 2022–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

ICLR (2) ICML (2) ECCV (1)

Top co-authors

Pascal Frossard (5) Francois Fleuret (4) Guillermo Ortiz-Jimenez (2) Ke Wang (2) Ahmet Caner Yüzügüler (1) Alessandro Favero (1)

Research topics

Machine Learning (4) Application Areas (2) Learning Types (2) Artificial Intelligence (1) Deep Learning (1) Core AI (1) Core Methods (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

model merging (2) multi-task learning (2) multi-objective optimization (1) ensemble method (1) pareto front (1) layer scaling (1) low-rank adapter (1) neural network (1) pareto front learning (1) weight space ensemble (1) catastrophic weights (1) consensus merging (1) selfish weights (1) tall-masks (1) catastrophic forgetting (1) task information (1) transfer learning (1)

Papers

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging ICLR 2025 Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences ICLR 2025 Localizing Task Information for Improved Model Merging and Compression ICML 2024 Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models ICML 2023 U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search ECCV 2022