I study how biological learning mechanisms and logic-based systems can guide the development of more efficient and robust machine learning architectures. My work bridges neuromorphic computing, formal methods, and deep learning, exploring diverse modes of learning—from spike-based plasticity and neural dynamics to symbolic structure discovery. I am passionate about uncovering shared principles between brains and algorithms, and leveraging them to advance intelligent systems that learn efficiently, reason reliably, and generalize well.
Mechanics of Learned Reasoning 1: TempoBench, A Benchmark for Interpretable Deconstruction
of Reasoning System Performance on Temporal Reasoning.
Under submission at OOPSLA 2026. We created a benchmark for interpretable deconstruction of reasoning system performance on temporal reasoning. We show how this can be used to understand the behavior of large language models and other learned reasoning systems.
AI Generated Podcast For Paper
AI-generated podcast discussion of the TempoBench paper
SNNs Are Not Transformers (Yet)
Spiking Neural Networks are a biologically plausible architectures with much greater energy efficiency then current deep learning architectures. Despite this, these models have faced slow adoption. We derive a sample complexity for these models and show how this scales with respect to longer input sequences. This demonstrates some of the weakness in these models in being adopted for language modeling. This work was presented at the SHDA Workshop in conjunction with the International Conference on Supercomputing and is currently under review for the Neuromorphic Computing and Engineering Journal.
Multi-Agent Path Planning for Cops And Robbers Via Reactive Synthesis
We are using Temporal Stream Logic (TSL) to create correct by construction coordinated systems for generating solutions to the Graph Theory Game Cops and Robbers
Conference Talks
| Amherst College AI in Liberal Arts | A Better Path Forward: Reconciling AI's Drive for Scale With the Reality of Its Energy Costs | View Slides |
| FMCAD | Automata Learning Meets State Space Machines | View Slides |
| SHDA Workshop ICS | SNNs Are Not Transformers (Yet) | View Slides |