Scholar
Ashutosh Trivedi
Google Scholar ID: 9WDXyy4AAAAJ
Associate Professor, University of Colorado at Boulder
Citations & Impact
Citations
1,267
H-index
16
i10-index
31
Publications
20
Co-authors
97
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published at AAAI 2023 and RTSS 2021: Reinforcement learning for cardiac pacemaker design based on formal safety requirements
- Accepted at ACL 2025: Grounding large language model outputs in logical reasoning using SAT solvers
- Published at NeurIPS 2022: Structured interactions in recursive Markov decision processes
- Published at CAV 2024: Encoding state and experience representations in RL using formal languages
- Published at ICSE 2023: Capturing legal obligations and fairness constraints using formal logic
- Accepted at ASE 2025: 'Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations'
- Accepted at CDC 2025: 'Objective Improvement Algorithm for Controller Synthesis in Uncertain Environments'
- Accepted at ICSE 2026: 'An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software'
- Presented a DIMAP seminar on Hyperproperties at the University of Warwick in June 2025
- AI explainability research on Sudoku featured in CNET in August 2025
Background
- Associate Professor of Computer Science at the University of Colorado Boulder
- Research focuses on making AI systems more trustworthy—ensuring they behave safely, fairly, and responsibly even as they learn and adapt
- Integrates formal methods (e.g., formal languages, automata, logic) with AI to enable explainable, reliable, and verifiable human-AI collaboration
- Emphasizes principled AI interaction: enabling humans to communicate goals, constraints, and expectations in precise, transparent, and verifiable ways
- Research interests include: Safety in AI, Reinforcement Learning, Formal Methods, Software Fairness, and Software Accountability
- Member of the Programming Languages and Verification (CUPLV) group
