← Search

Yinsong Yan

2 accepted papers

2026

Advancing Spatiotemporal Representations in Spiking Neural Networks via Parametric Invertible Transformation

ICLR 2026poster

Spiking Neural Networks (SNNs) are regarded as energy-efficient neural architectures due to their event-driven, spike-based computation paradigm. However, existing SNNs suffer from two fundamental limitations: (1) the constrained representational space imposed by binary spike firing mechanisms, whic…

Cited by 0SourceScholar
2025

KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling

ICML 2025poster

Determining the similarity between dynamical systems remains a long-standing challenge in both machine learning and neuroscience. Recent works based on Koopman operator theory have proven effective in analyzing dynamical similarity by examining discrepancies in the Koopman spectrum. Nevertheless, ex…