Cover Image

On Task Vectors and Gradients

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Luca, Solombrino, Daniele, Crisostomi, Donato, Bucarelli, Maria Sofia, D'Inverno, Giuseppe Alessio, Silvestri, Fabrizio, Rodolà, Emanuele
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ATM: Improving Model Merging by Alternating Tuning and Merging
by: Zhou, Luca, et al.
Published: (2024)

Task Singular Vectors: Reducing Task Interference in Model Merging
by: Gargiulo, Antonio Andrea, et al.
Published: (2024)

A topological description of loss surfaces based on Betti Numbers
by: Bucarelli, Maria Sofia, et al.
Published: (2024)

MASS: MoErging through Adaptive Subspace Selection
by: Crisostomi, Donato, et al.
Published: (2025)

Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models
by: Marincione, Davide, et al.
Published: (2025)

Metric Based Few-Shot Graph Classification
by: Crisostomi, Donato, et al.
Published: (2022)

Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
by: Wani, Farooq Ahmad, et al.
Published: (2023)

$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning
by: Trippa, Daniel, et al.
Published: (2024)

Language Models are Injective and Hence Invertible
by: Nikolaou, Giorgos, et al.
Published: (2025)

Model Merging: Foundations and Algorithms
by: Crisostomi, Donato
Published: (2026)

Mergenetic: a Simple Evolutionary Model Merging Library
by: Minut, Adrian Robert, et al.
Published: (2025)

MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs
by: Mencattini, Tommaso, et al.
Published: (2025)

Comparison of Reservoir Computing topologies using the Recurrent Kernel approach
by: D'Inverno, Giuseppe Alessio, et al.
Published: (2024)

Zero-Shot Quantization via Weight-Space Arithmetic
by: Solombrino, Daniele, et al.
Published: (2026)

Two-Scale Latent Dynamics for Recurrent-Depth Transformers
by: Pappone, Francesco, et al.
Published: (2025)

Implicit Inversion turns CLIP into a Decoder
by: D'Orazio, Antonio, et al.
Published: (2025)

Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs
by: Beddar-Wiesing, Silvia, et al.
Published: (2022)

The Majority Vote Paradigm Shift: When Popular Meets Optimal
by: Purificato, Antonio, et al.
Published: (2025)

VC dimension of Graph Neural Networks with Pfaffian activation functions
by: D'Inverno, Giuseppe Alessio, et al.
Published: (2024)

Multi-Way Representation Alignment
by: Achara, Akshit, et al.
Published: (2026)

$C^2M^3$: Cycle-Consistent Multi-Model Merging
by: Crisostomi, Donato, et al.
Published: (2024)

Communicating Sound Through Natural Language
by: Rossi, Emanuele, et al.
Published: (2026)

Surrogate models for diffusion on graphs via sparse polynomials
by: D'Inverno, Giuseppe Alessio, et al.
Published: (2025)

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
by: Mozafari, Mostafa, et al.
Published: (2025)

Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
by: Rinaldi, Filippo, et al.
Published: (2025)

LoopGen: Training-Free Loopable Music Generation
by: Marincione, Davide, et al.
Published: (2025)

Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves
by: Borgi, Alessio, et al.
Published: (2025)

Advancing Wildfire Risk Prediction via Morphology-Aware Curriculum Contrastive Learning
by: Scudo, Fabrizio Lo, et al.
Published: (2025)

Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data
by: Hirose, Osamu, et al.
Published: (2026)

Physics-Informed GNN for non-linear constrained optimization: PINCO a solver for the AC-optimal power flow
by: Varbella, Anna, et al.
Published: (2024)

Not All Latent Spaces Are Flat: Hyperbolic Concept Control
by: Briglia, Maria Rosaria, et al.
Published: (2026)

Revisiting Deep Information Propagation: Fractal Frontier and Finite-size Effects
by: D'Inverno, Giuseppe Alessio, et al.
Published: (2025)

Data-driven multi-agent modelling of calcium interactions in cell culture: PINN vs Regularized Least-squares
by: Poggi, Aurora, et al.
Published: (2025)

On the approximation capability of GNNs in node classification/regression tasks
by: D'Inverno, Giuseppe Alessio, et al.
Published: (2021)

PISA: Prioritized Invariant Subgraph Aggregation
by: Ghasemi, Ali, et al.
Published: (2025)

Beyond Position: the emergence of wavelet-like properties in Transformers
by: Ruscio, Valeria, et al.
Published: (2024)

Link Prediction with Physics-Inspired Graph Neural Networks
by: Di Francesco, Andrea Giuseppe, et al.
Published: (2024)

Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model
by: Di Nepi, Gavriel, et al.
Published: (2025)

TOAST: Transformer Optimization using Adaptive and Simple Transformations
by: Cannistraci, Irene, et al.
Published: (2024)

Select, Label, Evaluate: Active Testing in NLP
by: Purificato, Antonio, et al.
Published: (2026)