1

Camoscio: an Italian Instruction-tuned LLaMA
In recent years Large Language Models (LLMs) have increased the state of the art on several natural language processing tasks. However, …
Cite PDF GitHub Best Student Paper Award
Camoscio: an Italian Instruction-tuned LLaMA
Latent Space Translation via Semantic Alignment
Different neural models often exhibit similar latent spaces when exposed to semantically similar data; however, this inherent …
Cite PDF URL GitHub
Latent Space Translation via Semantic Alignment
Leveraging sparse and shared feature activations for disentangled representation learning
Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on …
Cite URL PDF NeurIPS 2023 spotlight
Leveraging sparse and shared feature activations for disentangled representation learning
Continuous Vector Quantile Regression
Vector quantile regression (VQR) estimates the conditional vector quantile function (CVQF), a fundamental quantity which fully …
Cite PDF URL
Continuous Vector Quantile Regression
AVEN-GR: Attribute Value Extraction and Normalization using product GRaphs
Getting a good understanding of the user intent is vital for e-commerce applications to surface the right product to a given customer …
Cite URL
AVEN-GR: Attribute Value Extraction and Normalization using product GRaphs
Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware Losses
Datasets used to train deep learning models in industrial settings often exhibit skewed distributions with some samples repeated a …
Cite URL
Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware Losses
Fauno - The Italian Large Language Model that will leave you senza parole!
This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). Our goal with Fauno is …
Cite PDF GitHub
Fauno - The Italian Large Language Model that will leave you senza parole!
Adversarial Permutation Invariant Training for Universal Sound Separation
Universal sound separation consists of separating mixes with arbitrary sounds of different types, and permutation invariant training …
Cite URL arXiv
Adversarial Permutation Invariant Training for Universal Sound Separation
Accelerating Transformer Inference for Translation via Parallel Decoding
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network …
PDF Cite arXiv GitHub
Accelerating Transformer Inference for Translation via Parallel Decoding
Multimodal Neural Databases
The rise in loosely-structured data available through text, images, and other modalities has called for new ways of querying them. …
PDF Cite arXiv
Multimodal Neural Databases