Arth Singh (Preferred)
Arth Singh
Researcher, AI Safety, AIM Intelligence
Researcher, Jinesis Lab, Department of Computer Science, University of Toronto
Joined
January 2026
Names
Emails
****@aim-intelligence.com (Confirmed)
****@gmail.com (Confirmed)
Personal Links
Career & Education History
Researcher
AI Safety, AIM Intelligence (aim-intelligence.com)
2025 – Present
Researcher
Jinesis Lab, Department of Computer Science, University of Toronto (cs.toronto.edu)
2025 – Present
Advisors, Relations & Conflicts
Expertise
physical AI safety
, embodied agents
, safe deployment
, world models
2025 – Present
cross-lingual NLP
, safety benchmarks
, multilingual evaluation
2025 – Present
AI safety
, adversarial robustness
, red teaming
, LLM evaluation
2024 – Present
mechanistic interpretability
, sparse autoencoders
, representation learning
2024 – Present