GUIDANCE (Debugging Computer Vision Models via Controlled Cross-modal Generation) FIS2023-03251 – CUP E53C25000420001 -and approved for financing with D.D. prot. n. 7206 of 04/17/2025

Position: Post-doctoral research appointment Institute: Uni. Trento
Posted on: 09/06/2026 Deadline: 30/06/2026

Scientific-Disciplinary Group

09/IINF-05 - Information Processing Systems

Description

This research focuses on developing self-evolving intelligent systems that combine hierarchical cognitive memory with adaptive multimodal reasoning. The goal is to enable systems to accumulate experience, retain structured knowledge, and improve autonomously over time in complex real-world environments. The work advances long-context Vision–Language Models (VLMs) and Multimodal Large Language Models (MLLMs) capable of reasoning over extended visual and textual inputs.

Number of positions

1

Funding body

Università di Trento