AI Researcher & Ph.D. Candidate specializing in Advanced Machine Learning, Topological Data Analysis (TDA), and Multimodal Representation Learning for complex, non-stationary time-series data.

My research centers on developing robust data-driven models capable of extracting faint signals from high-noise, high-dimensional environments. Specifically, my work in AI for Neuroscience involves pioneering multi-view adaptive fusion attention mechanisms and topological frameworks to model neural dynamics (EEG) for seizure detection and prediction.

The mathematical essence of my work, which includes detecting regime shifts, filtering micro-structure noise, and fusing multi-view spatiotemporal features, connects complex biological signals with real-world industrial challenges, including quantitative finance and financial time-series anomaly detection.

Driven by a passion for solving hard sequence-modeling problems, I welcome connections spanning Advanced AI Research, Quantitative Research, and Deep Learning Engineering.

Key Expertise: Deep Learning, Topological Data Analysis (TDA), Spatiotemporal Time-Series, Multimodal Fusion, Attention Mechanisms, Python/C++.