127 citations · 319 across the 41 of their papers we have counts for
45 papers
IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs
Pietro Moriello, Pietro Buzzega, Angelo Porrello +1
We introduce IrekoGPT, a post-hoc method for converting pretrained LLMs into slimmable models whose width can be adjusted at inference time. Building on SliceGPT, we retain its pro…
Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic
Francesca Morandi, Omayma Moussadek, Federico Venturini +5
Open Vocabulary Action Recognition (OVAR) enables the recognition of novel actions by leveraging vision-language representations, overcoming the limitations of traditional closed-s…
CAMASA: A CAM-based Dataset from the MASA Living Lab
Salvatore Iandolo, Marco Savarese, Gaetano Orazio Cauchi +5
Trajectory prediction is a key enabler of autonomous and cooperative driving systems. However, most existing benchmarks are either sensor-centric, geographically constrained, or ba…
Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic
Thomas Sommariva, Francesca Morandi, Simone Calderara +1
Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning through subtraction. Fine-tuning…
Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies
Carlos Garrido-Munoz, Aniello Panariello, Silvia Cascianelli +4
Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples fro…
ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection
Mattia Bernardi, Chiara Cappellino, Matteo Mosconi +3
Although recent Open-Vocabulary Object Detection architectures, such as Grounding DINO, demonstrate strong zero-shot capabilities, their performance degrades significantly under do…
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
Angelo Porrello, Pietro Buzzega, Felix Dangel +4
Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation dri…
Transporting Task Vectors across Different Architectures without Training
Filippo Rinaldi, Aniello Panariello, Giacomo Salici +2
Adapting large pre-trained models to downstream tasks often produces task-specific parameter updates that are expensive to relearn for every model variant. While recent work has sh…
CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction
Mattia Grasselli, Angelo Porrello, Carlo Augusto Grazia
Autonomous driving remains a challenging task, particularly due to safety concerns. Modern vehicles are typically equipped with expensive sensors such as LiDAR, cameras, and radars…
Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
Filippo Rinaldi, Aniello Panariello, Giacomo Salici +4
When a new release of a foundation model is published, practitioners typically need to repeat fine-tuning, even if the same task was already tackled in the previous version. A prom…
Accurate and Efficient Low-Rank Model Merging in Core Space
Aniello Panariello, Daniel Marczak, Simone Magistri +5
In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as…
Rethinking Layer-wise Model Merging through Chain of Merges
Pietro Buzzega, Riccardo Salami, Angelo Porrello +1
Fine-tuning pretrained models has become a standard pathway to achieve state-of-the-art performance across a wide range of domains, leading to a proliferation of task-specific mode…
Modular Embedding Recomposition for Incremental Learning
Aniello Panariello, Emanuele Frascaroli, Pietro Buzzega +3
The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficie…
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli +6
Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g.,…
How to Train Your Metamorphic Deep Neural Network
Thomas Sommariva, Simone Calderara, Angelo Porrello
Neural Metamorphosis (NeuMeta) is a recent paradigm for generating neural networks of varying width and depth. Based on Implicit Neural Representation (INR), NeuMeta learns a conti…
DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
Chiara Cappellino, Gianluca Mancusi, Matteo Mosconi +3
Open-Vocabulary object detectors can generalize to an unrestricted set of categories through simple textual prompting. However, adapting these models to rare classes or reinforcing…
Is Multiple Object Tracking a Matter of Specialization?
Gianluca Mancusi, Mattia Bernardi, Aniello Panariello +3
End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses signifi…
May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
Monica Millunzi, Lorenzo Bonicelli, Angelo Porrello +3
Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data…
An Attention-based Representation Distillation Baseline for Multi-Label Continual Learning
Martin Menabue, Emanuele Frascaroli, Matteo Boschini +3
The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Mos…
CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning
Emanuele Frascaroli, Aniello Panariello, Pietro Buzzega +3
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learni…
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
Matteo Mosconi, Andriy Sorokin, Aniello Panariello +6
The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of…
Trajectory Forecasting through Low-Rank Adaptation of Discrete Latent Codes
Riccardo Benaglia, Angelo Porrello, Pietro Buzzega +2
Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e.g. basketball players engaged in intri…
A Second-Order Perspective on Model Compositionality and Incremental Learning
Angelo Porrello, Lorenzo Bonicelli, Pietro Buzzega +3
The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model…
Selective Attention-based Modulation for Continual Learning
Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi +5
We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiolog…