Quantization has significantly improved the compute and memory efficiency of Large Language Model (LLM) training. However, existing approaches still rely on acc...
Evaluating Large Language Model (LLM) applications differs from traditional software testing because outputs are stochastic, high-dimensional, and sensitive to ...
Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) oper...
Unsupervised text segmentation is crucial because boundary labels are expensive, subjective, and often fail to transfer across domains and granularity choices. ...
Introduction In a world inundated with information, understanding the connections between different pieces of content can be a daunting task. This is particula...
Frontier LLMs are increasingly utilised across academia, society and industry. A commonly used unit for comparing models, their inputs and outputs, and estimati...
Large reasoning models (LRMs) produce a textual chain of thought (CoT) in the process of solving a problem, which serves as a potentially powerful tool to under...
Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior w...
The integration of AI agents into economic markets fundamentally alters the landscape of strategic interaction. We investigate the economic implications of expa...
In the generative AI era, where even critical medical tasks are increasingly automated, radiology report generation (RRG) continues to rely on suboptimal metric...
As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and compu...
Information overload and misinformation create significant challenges in extracting meaningful narratives from large news collections. This paper defines the na...
