3 papers
hep-ex2026
Better Queries, Cheaper Attention: Adapting Transformers for Efficient Sparse Reconstruction
Philippa Duckett, Samuel Van Stroud, Max Hart +2
Query-based transformer decoders are effective for object reconstruction from sparse scientific sensor measurements, but their scalability to high-multiplicity data is limited by f…
hep-ex2025
Transformers for Charged Particle Track Reconstruction in High Energy Physics
Samuel Van Stroud, Philippa Duckett, Max Hart +4
Reconstructing charged particle tracks is a fundamental task in modern collider experiments. The unprecedented particle multiplicities expected at the High-Luminosity Large Hadron…
cs.CL2024
Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt
Damien de Mijolla, Wen Yang, Philippa Duckett +2
Prompting and fine-tuning have emerged as two competing paradigms for augmenting language models with new capabilities, such as the use of tools. Prompting approaches are quick to…