Michael Moseley — accepted AI-conference papers

2025

LieRE: Lie Rotational Positional Encodings

Sophie Ostmeier, Brian Axelrod, Maya Varma, Michael Moseley, Akshay S Chaudhari, Curtis Langlotz

ICML 2025poster

Transformer architectures depend on explicit position encodings to capture token positional information. Rotary Position Encoding (RoPE) has emerged as a popular choice in language models due to its efficient encoding of relative position information through key-query rotations. However, RoPE faces…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

GREEN: Generative Radiology Report Evaluation and Error Notation

Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen +5

EMNLP 2024finding

Evaluating radiology reports is a challenging problem as factual correctness is extremely important due to its medical nature. Existing automatic evaluation metrics either suffer from failing to consider factual correctness (e.g., BLEU and ROUGE) or are limited in their interpretability (e.g., F1Che…

Cited by 19 Source ↗PDF ↗Scholar ↗