1 citations · 2 across the 4 of their papers we have counts for
5 papers
ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
Salvatore Romano, Marco Grassia, Pietro Liò +1
Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the c…
Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning
Salvatore Romano, Marco Grassia, Giuseppe Mangioni
Graph generation is a crucial task in many fields, including network science and bioinformatics, as it enables the creation of synthetic graphs that mimic the properties of real-wo…
DSA, AIA, and LLMs: Approaches to conceptualizing and auditing moderation in LLM-based chatbots across languages and interfaces in the electoral contexts
Natalia Stanusch, Raziye Buse Cetin, Salvatore Romano +4
The integration of Large Language Models (LLMs) into chatbot-like search engines poses new challenges for governing, assessing, and scrutinizing the content output by these online…
AI-Generated Algorithmic Virality
Natalia Stanusch, Martin Degeling, Salvatore Romano +3
There is a growing discussion about social media feeds being increasingly filled with AI-generated content. Due to its visual plausibility, low cost, and fast production speed, AI-…
TikTok's Research API: Problems Without Explanations
Carlos Entrena-Serrano, Martin Degeling, Salvatore Romano +1
Following the Digital Services Act of 2023, which requires Very Large Online Platforms (VLOPs) and Very Large Online Search Engines (VLOSEs) to facilitate data accessibility for in…