Cover Image

Accurate and Efficient Low-Rank Model Merging in Core Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Panariello, Aniello, Marczak, Daniel, Magistri, Simone, Porrello, Angelo, Twardowski, Bartłomiej, Bagdanov, Andrew D., Calderara, Simone, van de Weijer, Joost
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
by: Marczak, Daniel, et al.
Published: (2025)

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
by: Magistri, Simone, et al.
Published: (2026)

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
by: Goswami, Dipam, et al.
Published: (2024)

Transporting Task Vectors across Different Architectures without Training
by: Rinaldi, Filippo, et al.
Published: (2026)

Is Multiple Object Tracking a Matter of Specialization?
by: Mancusi, Gianluca, et al.
Published: (2024)

Modular Embedding Recomposition for Incremental Learning
by: Panariello, Aniello, et al.
Published: (2025)

CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning
by: Frascaroli, Emanuele, et al.
Published: (2024)

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
by: Goswami, Dipam, et al.
Published: (2026)

Monocular Per-Object Distance Estimation with Masked Object Modeling
by: Panariello, Aniello, et al.
Published: (2024)

An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates
by: Soutif--Cormerais, Albin, et al.
Published: (2024)

Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
by: Rinaldi, Filippo, et al.
Published: (2025)

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
by: Magistri, Simone, et al.
Published: (2025)

Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
by: Magistri, Simone, et al.
Published: (2024)

Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies
by: Garrido-Munoz, Carlos, et al.
Published: (2026)

Trajectory Forecasting through Low-Rank Adaptation of Discrete Latent Codes
by: Benaglia, Riccardo, et al.
Published: (2024)

Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
by: Mosconi, Matteo, et al.
Published: (2024)

How to Train Your Metamorphic Deep Neural Network
by: Sommariva, Thomas, et al.
Published: (2025)

MagMax: Leveraging Model Merging for Seamless Continual Learning
by: Marczak, Daniel, et al.
Published: (2024)

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
by: Goswami, Dipam, et al.
Published: (2024)

Exemplar-free Continual Representation Learning via Learnable Drift Compensation
by: Gomez-Villa, Alex, et al.
Published: (2024)

Rethinking Layer-wise Model Merging through Chain of Merges
by: Buzzega, Pietro, et al.
Published: (2025)

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
by: Goswami, Dipam, et al.
Published: (2023)

SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
by: Caselli, Lorenzo, et al.
Published: (2026)

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
by: Cignoni, Giacomo, et al.
Published: (2026)

On the importance of cross-task features for class-incremental learning
by: Soutif--Cormerais, Albin, et al.
Published: (2021)

Revisiting Supervision for Continual Representation Learning
by: Marczak, Daniel, et al.
Published: (2023)

ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection
by: Bernardi, Mattia, et al.
Published: (2026)

An Attention-based Representation Distillation Baseline for Multi-Label Continual Learning
by: Menabue, Martin, et al.
Published: (2024)

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
by: Cappellino, Chiara, et al.
Published: (2025)

Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
by: Rypeść, Grzegorz, et al.
Published: (2023)

Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic
by: Sommariva, Thomas, et al.
Published: (2026)

May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
by: Millunzi, Monica, et al.
Published: (2024)

Selective Attention-based Modulation for Continual Learning
by: Bellitto, Giovanni, et al.
Published: (2024)

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
by: Goswami, Dipam, et al.
Published: (2024)

Parameter-Efficient Interventions for Enhanced Model Merging
by: Osial, Marcin, et al.
Published: (2024)

Self-Labeling the Job Shop Scheduling Problem
by: Corsini, Andrea, et al.
Published: (2024)

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
by: Goswami, Dipam, et al.
Published: (2025)

Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
by: Pawlak, Stanisław, et al.
Published: (2025)

How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models
by: Trinci, Tomaso, et al.
Published: (2024)

Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
by: Yu, Lu, et al.
Published: (2024)