← Search

Filippo Ziliotto

2 accepted papers

2026

PersONAL: Towards a Comprehensive Benchmark for Personalized Embodied Agents

ICRA 2026poster

Recent advances in Embodied AI have enabled agents to perform increasingly complex tasks and adapt to diverse environments. However, deploying such agents in realistic human-centered scenarios, such as domestic households, remains challenging, particularly due to the difficulty of modeling individua…

2025

TANGO: Training-free Embodied AI Agents for Open-world Tasks

CVPR 2025poster

Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we propose TANGO, an approach that extends the program composition via LLMs already observed for images, a…

Cited by 0SourcePDFScholar