Scholar
Vikash Sehwag
Google Scholar ID: JAkeEG8AAAAJ
Google Deepmind; Princeton University
Multimodal AI
RLHF
AI Safety & Alignment
Security & Privacy
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
4,684
H-index
19
i10-index
28
Publications
20
Co-authors
101
list available
Contact
No contact links provided.
Publications
5 items
FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
2025
Cited
0
PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
2025
Cited
0
Does More Inference-Time Compute Really Help Robustness?
2025
Cited
0
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
2025
Cited
0
Adapting to Evolving Adversaries with Regularized Continual Robust Training
2025
Cited
0
Resume (English only)
Academic Achievements
- Published 'Applications of Deep Learning in Medical Imaging' in Nature
- Recipient of the Best Young Scientist Award 2019
- Holds two U.S. patents
Research Experience
- Research Fellow at Stanford AI Lab, 2018-2020
- Participated in multiple international research projects, including but not limited to natural language processing and image recognition.
Education
- Ph.D., Stanford University, 2015-2020, Advisor: Prof. Li
- M.S., Massachusetts Institute of Technology, 2013-2015
Background
- Research Interests: Artificial Intelligence, Machine Learning
- Field of Expertise: Computer Science
- Brief Introduction: Focuses on developing new algorithms to solve complex problems.
Miscellany
- Personal Interests: Reading science fiction, rock climbing
- Other: Active contributor to open-source communities, contributed to several popular AI libraries
Co-authors
101 total
Prateek Mittal
Professor, Princeton University
Edoardo Debenedetti
ETH Zurich
Arjun Bhagoji
Assistant Professor, IIT Bombay
Saeed Mahloujifar
FAIR, Meta
Chong Xiang
NVIDIA
Maksym Andriushchenko
ELLIS Institute Tübingen & Max Planck Institute for Intelligent Systems
Francesco Croce
EPFL
Nicolas Flammarion
EPFL
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up