Skip to content

Author

Enzo Tartaglione

We have 5 of 53 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models

Prompt learning adapts vision-language models such as CLIP by optimizing a short learnable prompt. The cross-entropy objective pulls this prompt toward base-class specialization, whereas generalization to unseen classes benefits from staying close to CLIP's zero-shot feature space. Because both objectives act on the sa...

Imad Eddine Marouf, Khalid Oublal, Enzo Tartaglione et al. · 0 citations
#machine learning Preprint Nov 2026

Exploiting Biases in Attention for Transformers

Attention is known to be sparse in vision transformers. In particular, we analyze the unequal relevance of attention-matrix columns to the final computation and show that this phenomenon becomes increasingly pronounced with network depth. This can be interpreted as saying that tokens have an absolute importance for the...

Charles Herr, Gabriele Spadaro, Enzo Tartaglione · 0 citations
#machine learning Preprint Sep 2026

Validity-Preserving Hierarchical RL for Joint Routing and Switch Placement in EDA

Routing and switch placement are fundamental combinatorial optimization problems in chip design, requiring the joint optimization of routing topology and physical placement under strict structural, geometric and logical constraints. Existing approaches typically rely on carefully engineered heuristics that incorporate...

Dorian Gailhard, Ugo Lecerf, Enzo Tartaglione et al. · 0 citations
Conference Open access Aug 2026

CutClean: Neural Network Pruning for Privacy-Preserving Inference

CutClean is a privacy-aware pruning method that allows to reduce privacy information flow through the network, while increasing its sparsity, and effectively minimizes private information flow while achieving high sparsity rates and preserving classification target accuracy.

Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise et al. · 0 citations
#machine learning Preprint Sep 2026

From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy

This work proposes an efficient strategy that enables merging of layers without an existing analytical solution, and also without increasing kernel size, and validate the approach across multiple architectures and datasets, and measure inference speed-up gains on real embedded platforms.

P. Shul'zhenko, Gabriele Spadaro, Enzo Tartaglione · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.