activity
20242026
collaborators

5 papers

astro-ph.SR2026

SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions

Spiridon Kasapis, Eren Dogan, Irina N. Kitiashvili +6

The development of accurate forecasts of solar eruptive activity has become increasingly important for preventing potential impacts on space technologies and exploration. Therefore…

astro-ph.SR2026

Forecasting Continuum Intensity for Solar Active Region Emergence Prediction using Transformers

Jonas Tirona, Sarang Patil, Spiridon Kasapis +5

Early and accurate prediction of solar active region (AR) emergence is crucial for space weather forecasting. Building on established Long Short-Term Memory (LSTM) based approaches…

cs.AI2025

Hyperbolic Large Language Models

Sarang Patil, Zeyong Zhang, Yiran Huang +2

Large language models (LLMs) have achieved remarkable success and demonstrated superior performance across various tasks, including natural language processing (NLP), weather forec…

cs.CL2025

Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings

Sarang Patil, Ashish Parmanand Pandey, Ioannis Koutis +1

Selective state-space models excel at long-sequence modeling, but their capacity for language representation -- in complex hierarchical reasoning -- remains underexplored. Most lar…

cs.LG2024

A Comparative Study on Dynamic Graph Embedding based on Mamba and Transformers

Ashish Parmanand Pandey, Alan John Varghese, Sarang Patil +1

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise…