collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Compositional Generalization in Autoregressive Models via Logit Composition

Aakash Kumar, Maria Sofia Bucarelli, Emanuele Natale

Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks. We introduce a new and pri…

cs.LG2026

MASS: MoErging through Adaptive Subspace Selection

Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo +5

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training over…

cs.LG2026

Energy Guided smoothness to improve Robustness in Graph Classification

Farooq Ahmad Wani, Maria Sofia Bucarelli, Andrea Giuseppe Di Francesco +2

Graph Neural Networks (GNNs) are powerful at solving graph classification tasks, yet applied problems often contain noisy labels. In this work, we study GNN robustness to label noi…

cs.LG2026

Early-Exit Graph Neural Networks

Andrea Giuseppe Di Francesco, Maria Sofia Bucarelli, Franco Maria Nardini +3

Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy inputs while retaining full-depth accurac…

cs.LG2025

PISA: Prioritized Invariant Subgraph Aggregation

Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli +1

Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and di…

cs.LG2025

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic

Mostafa Mozafari, Farooq Ahmad Wani, Maria Sofia Bucarelli +1

Corrupted training data are ubiquitous. Corrective Machine Unlearning (CMU) seeks to remove the influence of such corruption post-training. Prior CMU typically assumes access to id…