Alessio Galatolo — accepted AI-conference papers

2026

Lightweight Visual Reasoning for Socially-Aware Robots

Alessio Galatolo, Ronald Cumbal, Alexandros Rouchitsas, Katie Winkle, Didem Gurdur Broo, Ginevra Castellano

ICRA 2026poster

Robots operating in shared human environments must not only navigate, interact, and detect their surroundings, they must also interpret and respond to dynamic, and often unpredictable, human behaviours. Although recent advances have shown promise in enhancing robotic perception and instruction-follo…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models

Alessio Galatolo, Zhenbang Dai, Katie Winkle, Meriem Beloucif

ACL 2025finding

Fine-tuning Large Language Models (LLMs) with first-order methods like back-propagation is computationally intensive. Zeroth-Order (ZO) optimisation uses function evaluations instead of gradients, reducing memory usage, but suffers from slow convergence in high-dimensional models. As a result, ZO re…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Memory-Augmenting Decoder-Only Language Models through Encoders (Student Abstract)

Alessio Galatolo, Katie Winkle

AAAI 2024technical

The Transformer architecture has seen a lot of attention in recent years also thanks to its ability to scale well and allow massive parallelism during training. This has made possible the development of Language Models (LMs) of increasing size and the discovery of latent abilities that completely ou…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗