Weigao Sun

Data Mining in the Big Data Era

2022 · Advances in Social Science, Education and Humanities Research/Advances in social science, education and humanities research

While entering into the era of big data, seeking the secrets hidden in the data has become the main target in every single industry. This paper states the definition of data mining in the era …

Scaling Laws for Linear Complexity Language Models

2024 · arXiv (Cornell University)

The interest in linear complexity models for large language models is on the rise, although their scaling capacity remains uncertain. In this study, we present the scaling laws for linear complexity language models to establish …

Comba: Improving Bilinear RNNs with Closed-loop Control

2025 · arXiv (Cornell University)

Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Delta learning rule. Unlike previous state-space models (e.g., Mamba) and gated linear …