3 papers
cs.CV2026
Zero-Shot Quantization via Weight-Space Arithmetic
Daniele Solombrino, Antonio Andrea Gargiulo, Alessandro Zirilli +3
We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantization vector: extracted from a donor task…
cs.LG2025
On Task Vectors and Gradients
Luca Zhou, Daniele Solombrino, Donato Crisostomi +4
Task arithmetic has emerged as a simple yet powerful technique for model merging, enabling the combination of multiple finetuned models into one. Despite its empirical success, a c…
cs.LG2025
ATM: Improving Model Merging by Alternating Tuning and Merging
Luca Zhou, Daniele Solombrino, Donato Crisostomi +3
Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In thi…