5 papers
MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network
Matthew Raffel, Adwaith Renjith, Lizhong Chen
Kolmogorov-Arnold Networks (KANs) replace scalar weights with per-edge vectors of basis coefficients, thereby increasing expressivity and accuracy while also resulting in a multipl…
FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer
Matthew Raffel, Lizhong Chen
The Kolmogorov-Arnold Network (KAN) has been gaining popularity as an alternative to the multilayer perceptron (MLP) due to its greater expressiveness and interpretability. Even so…
Towards Universal Semantics With Large Language Models
Raymond Baartmans, Matthew Raffel, Rahul Vikram +2
The Natural Semantic Metalanguage (NSM) is a linguistic theory based on a universal set of semantic primes: simple, primitive word-meanings that have been shown to exist in most, i…
BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System
Matthew Raffel, Victor Agostinelli, Lizhong Chen
This paper discusses the construction, fine-tuning, and deployment of BeaverTalk, a cascaded system for speech-to-text translation as part of the IWSLT 2025 simultaneous translatio…
Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation
Matthew Raffel, Victor Agostinelli, Lizhong Chen
Large language models (LLMs) have achieved state-of-the-art performance in various language processing tasks, motivating their adoption in simultaneous translation. Current fine-tu…