📝 Paper accepted at ECCV 26 🎉
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
Francesco Taioli
PhD in Artificial Intelligence
I am an Applied Scientist at Amazon, based in Madrid.
I obtained my PhD (cum laude) in the National PhD Programme in Artificial Intelligence at the Polytechnic of Turin, under the supervision of Prof. Marco Cristani and Prof. Alessandro Farinelli.
My PhD research followed three main directions: (i) leveraging VLMs/VLAs for spatial reasoning in navigation; (ii) uncertainty-aware navigation and human-agent interaction for handling instruction ambiguity; and (iii) neural scene representations for language-grounded perception.
My work has appeared in top-tier venues, including ICCV, TPAMI, and IROS, with all code publicly available.
News
I joined Amazon as an Applied Scientist!
I joined Amazon as an Applied Scientist Intern!
Paper accepted at ICCV 25 🎉
What do human-agent bidirectional interaction, navigation, vision-language models, and hallucinations have in common? Read our new ICCV paper!
I've been recognized as an Outstanding Reviewer for CVPR25!
🤖 I co-organized the Human-aware Embodied AI workshop at IROS 2025!
Oral Presentation at IROS 2024! 🎉
Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation was accepted at IROS 2024, with an oral presentation!
CVPR 2024!
We had a paper accepted at the 5th Annual Embodied AI Workshop @ CVPR 2024. Moreover, we won the MultiON Challenge @ CVPR 2024!
I attended the International Computer Vision Summer School (ICVSS)!
Education & Work
Applied Scientist
Amazon, Madrid, Spain
Applied Scientist Intern
Amazon, Madrid, Spain
Visiting Research Student
Simon Fraser University, Vancouver, Canada
National Ph.D. Programme in Artificial Intelligence
Polytechnic of Turin, Turin, Italy
B.Sc. & M.Sc. in Computer Science & Engineering
University of Verona, Verona, Italy
Selected publications
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
F Taioli, Daniel Coelho, Iaroslav Melekhov, Roberto Alcover-Couso, Jose Miguel Grande Saiz, Virginia Fernandez Arguedas and Artur Bekasov
European Conference on Computer Vision (ECCV), 2026
Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues
F Taioli, E Zorzi, G Franchi, A Castellini, A Farinelli, M Cristani, Y Wang
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
Diffusion-based Image Generation for In-distribution Data Augmentation in Surface Defect Detection
L Capogrosso*, F Girella*, F Taioli*, MD Chiara, M Aqeel, F Fummi, F Setti, M Cristani
VISAPP - 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2024
Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation
F Taioli, S Rosa, A Castellini, L Natale, A Del Bue, A Farinelli, M Cristani, Y Wang
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Unsupervised Active Visual Search With Monte Carlo Planning Under Uncertain Detections
F Taioli, F Giuliari, Y Wang, R Berra, A Castellini, A Del Bue, A Farinelli, M Cristani
IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (12), 10375-10389, 2024
Language-Enhanced RNR-Map: Querying Renderable Neural Radiance Field Maps with Natural Language
F Taioli, F Cunico, F Girella, R Bologna, A Farinelli, M Cristani
IEEE/CVF International Conference on Computer Vision, 4669-4674, 2023
Reviewer Activity
Conferences
2026
- IROS 2026
2025
- CVPR 2025 Outstanding Reviewer
- ACL ARR 2025 Emergency Reviewer
- IROS 2025
- ICCV 2025
2024
- RO-MAN 2024
- ICRA 2024
- CVPR 2024
Journals
- IEEE Robotics and Automation Letters (RA-L) [25-26]