Taught CSCI 5444, Introduction to the Theory of Computation, in Fall 2025.
Our research on AI explainability in Sudoku was featured in CNET.
New arXiv preprint with Maria Leonor Pacheco, Fabio Somenzi, and Dananjay Srinivas: Explaining Hitori Puzzles: Neurosymbolic Proof Staging for Sequential Decisions.
Paper accepted at ASE 2025: Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations.
Paper accepted for presentation at CDC 2025: Objective Improvement Algorithm for Controller Synthesis in Uncertain Environments.
Gave a DIMAP seminar on hyperproperties at the University of Warwick.
Paper accepted to ICSE 2026: An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software. Authors: Sina Gogani Khiabani, Ashutosh Trivedi, Diptikalyan Saha, and Saeid Tizpaz-Niari.
Shadi Tasdighi Kalat successfully defended her thesis: Eliciting Decision Proxies in Multi-Agent Games.
Paper accepted to QEST+FORMATS: On Choice of Loss Functions for Neural Control Barrier Certificates. Authors: Alireza Nadali, Ashutosh Trivedi, and Majid Zamani.
Paper Stochastic Neural Simulation Relations for Transferring Control under Uncertainty received a NeuS 2025 Disruptive Idea Award.
Paper accepted to IJCAI: Continuous Time Reward Machines. Authors: Amin Falah, Shibashis Guha, and Ashutosh Trivedi.
NeuS'25 paper Stochastic Neural Simulation Relations for Transferring Control under Uncertainty accepted for oral presentation. Authors: Alireza Nadali, Ashutosh Trivedi, and Majid Zamani.
Mateo Perez successfully defended his thesis: Formal Languages and Automata for Reinforcement Learning.
John Komp successfully defended his thesis: From Text to Life: Optimized Pacemaker Therapy Through Formal Methods and Safe Reinforcement Learning.
Began my sabbatical at the University of Liverpool, UK.
I received the recognition of being named a Senior Member of the ACM.
Received the Royal Society Wolfson Visiting Fellowship.
We received a Distinguished Paper Award at CAV for our paper: Regular Reinforcement Learning.