Principal Researcher, GEHC
2 papers at NeurIPS 2025
A novel class of MTPP models inspired by linear Hawkes processes and deep state-space models, that brings linear complexity and sublinear scaling while being highly expressive.
We propose RBD, a plug-in module that detects and corrects biased LLM evaluations through structured reasoning, significantly improving accuracy, consistency, and scalability across multiple bias types and evaluator models.
