Homa Esfahanizadeh

InfoShape: Task-Based Neural Data Shaping via Mutual Information

2022 · arXiv (Cornell University)

The use of mutual information as a tool in private data sharing has remained an open challenge due to the difficulty of its estimation in practice. In this paper, we propose InfoShape, a task-based encoder …

MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression

2024 · arXiv (Cornell University)

Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train such LLMs require extensive resources including but not limited to large …