Francesco Pinto
Scholar

Francesco Pinto

Google Scholar ID: rqAdo2MAAAAJ
Research Scientist, Google Deepmind
Agentic AI Safety and Security
Google Scholar↗
Citations & Impact
All-time
Citations
650
 
H-index
11
 
i10-index
14
 
Publications
20
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
9 items
MAC: Multi-Agent Constitution Learning
2026
Cited
0
VMDT: Decoding the Trustworthiness of Video Foundation Models
2025
Cited
0
LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
2025
Cited
0
Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust
2025
Cited
0
Where You Place the Norm Matters: From Prejudiced to Neutral Initializations
2025
Cited
0
AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
2025
Cited
0
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
2025
Cited
0
Focus On This, Not That! Steering LLMs With Adaptive Feature Specification
arXiv.org · 2024
Cited
0
Resume (English only)
Co-authors
10 total
Philip Torr
Philip Torr
Professor, University of Oxford
Puneet K. Dokania
Puneet K. Dokania
University of Oxford | Bosch (Five AI)
Sernam Lim
Sernam Lim
Associate Professor, CS, University of Central Florida
Adam Davies
Adam Davies
PhD Candidate, University of Illinois Urbana-Champaign
Atılım Güneş Baydin
Atılım Güneş Baydin
University of Oxford
Giacomo Acciarini
Giacomo Acciarini
Research Fellow at European Space Agency, Advanced Concepts Team
Jianhao Yuan
Jianhao Yuan
University of Oxford
Fanny Yang
Fanny Yang
ETH Zurich