Skip Connections in Transformer Models
Luglio 5, 2025admin NUAI,Committee,Notizie,Uncategorized(0)This post is divided into three parts; they are: • Why Skip Connections are Needed...
Single Word Change is All You Need: Using LLMs to Create Synthetic Training Examples for Text Classifiers
Luglio 15, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2401.17196v3 Announce Type: replace Abstract: In text classification, creating an adversarial example means subtly perturbing...
SINAI at eRisk@CLEF 2025: Transformer-Based and Conversational Strategies for Depression Detection
Settembre 25, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2509.19861v1 Announce Type: new Abstract: This paper describes the participation of the SINAI-UJA team in...
Simulated Reasoning is Reasoning
Gennaio 6, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2601.02043v1 Announce Type: cross Abstract: Reasoning has long been understood as a pathway between stages...
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
Ottobre 9, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2505.16834v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs)...
Similarity-Distance-Magnitude Activations
Ottobre 31, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2509.12760v2 Announce Type: replace-cross Abstract: We introduce the Similarity-Distance-Magnitude (SDM) activation function, a more robust...
SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space
Febbraio 3, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2504.16315v3 Announce Type: replace-cross Abstract: The complexity of sign language data processing brings many challenges...
SignRAG: A Retrieval-Augmented System for Scalable Zero-Shot Road Sign Recognition
Dicembre 16, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2512.12885v1 Announce Type: cross Abstract: Automated road sign recognition is a critical task for intelligent...
Sigmoid vs ReLU Activation Functions: The Inference Cost of Losing Geometric Context
Aprile 9, 2026admin NUAI,Committee,Notizie,Uncategorized(0)A deep neural network can be understood as a geometric system, where each layer reshapes...
