Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
publications
Global, regional, and national epidemiology of ischemic stroke in young adults, 1990–2021
Published in Journal of Neurology, 272(5), 354 (2025)
A global epidemiological analysis of ischemic stroke in young adults (1990–2021), characterizing burden trends across regions and countries.
Development and validation of a web-based machine learning model for predicting early neurological deterioration following stroke thrombolysis: A multicenter study
Published in Journal of Medical Internet Research, 27, e77858 (2025)
Multicenter study (n=1,927) introducing ENDRAS, an XGBoost-based model using 6 routine clinical variables to predict END after thrombolysis and guide risk-stratified post-thrombolysis management.
CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency
Published in SIGKDD 2026 Research Track
CAAD reframes multivariate time series anomaly detection as continuous verification of Granger causality consistency, using multi-scale alignment and a dual causal scoring mechanism to detect stealthy industrial failures.
HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models
Published in arXiv:2605.24140, 2026
HyperGuide distills reasoning progress into a hyperbolic geometric signal that guides step-by-step LLM generation, yielding consistent gains especially on deeper reasoning chains.
SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction
Published in SDM 2026; Forecast@ICML26
SC-JEPA stabilizes JEPA-based latent predictive learning for time-series anomaly prediction via a soft codebook bottleneck and multi-resolution predictive objective.
Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
Published in arXiv:2605.19196, 2026
REFLECT introduces a meta-evaluation benchmark for LLM judges in agentic settings, revealing that even the best judges achieve below 55% accuracy on fine-grained failure detection.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.