Abstract: Denoising autoencoders have been previously shown to be competitive alternatives to restricted Boltzmann machines for unsupervised pretraining of each layer of a deep architecture. We show ...

Speculative decoding can help AI chatbots improve throughput and reduce hardware demand by using a smaller model to draft tokens that a larger model validates.

Abstract: Data-driven methods open up unprecedented possibilities for maritime surveillance using automatic identification system (AIS) data. In this work, we explore deep learning strategies using ...

Traditional Large Language Models (LLMs) rely on a tokenizer (like BPE or SentencePiece) to convert text into subword tokens before feeding them to the transformer. The Byte Latent Transformer ...

Pavan Subramani started doing molecular dynamics simulations for computational drug discovery alongside his high school coursework, sparking an interest in a STEM career.