Research
Papers, manuscripts, and open investigations
Research is presented as lab work rather than portfolio proof: abstract, problem statement, methodology, experimental design, results, limitations, future directions, references, and citation export.
Grokking Beyond Addition: Circuit-Level Analysis of Algebraic Learning in Transformers
This work extends grokking analysis beyond modular addition to eight algebraic operations across abelian fields, a composite ring, and non-abelian groups. A controlled transformer setup isolates when memorized algorithms become reusable circuits and when representation complexity blocks generalization.
Adaptive Tensor-Network Compression of LLMs: An Extension of CompactifAI
This project reproduces and extends CompactifAI-style tensor-network compression on real open-weight LLMs. It profiles layer sensitivity, replaces uniform bond dimensions with adaptive schedules, and evaluates healing runs across standard language benchmarks.
Credit Assignment in Spiking Neural Networks: Bridging Bioplausibility and Scalability
This investigation studies how scalable gradient methods and biologically plausible local learning rules diverge when training recurrent spiking neural networks on temporal tasks.