11 citations · 12 across the 6 of their papers we have counts for
6 papers
Semantic Adapter Routing with Fine-Tuning Task Embeddings
Enrico Cassano, Michał Brzozowski, Paolo Mandica +2
Parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. Given such a library, routing aims to s…
GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning
Paolo Mandica, Michał Brzozowski, Zuzanna Dubanowska +1
Low-rank adaptation (LoRA) has become a dominant paradigm for parameter-efficient fine-tuning (PEFT) of large-scale deep learning models. However, its bilinear parameterization ind…
Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution
Zuzanna Dubanowska, Maciej Żelaszczyk, Michał Brzozowski +2
We critically assess the efficacy of the current SOTA in hallucination detection and find that its performance on the RAGTruth dataset is largely driven by a spurious correlation w…
Hyperbolic Learning with Multimodal Large Language Models
Paolo Mandica, Luca Franco, Konstantinos Kallidromitis +2
Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image…
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
Luca Franco, Paolo Mandica, Konstantinos Kallidromitis +4
We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the h…
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
Luca Franco, Paolo Mandica, Bharti Munjal +1
Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the train…