Andreas Maier

WING achieves state-of-the-art CT synthesis from MRI and CBCT by transforming the regression target into windowed representations, significantly improving detail and accuracy.

A novel lightweight 3D detector achieves high organ localization accuracy in abdominal CT scans using pseudo-text conditioning, setting a new open-source benchmark.

A standardized dataset of over 9,000 high-voltage fault simulations could revolutionize the benchmarking of power system protection methods.

Dynamic interval encoding in QUBO-based CT reconstruction significantly enhances image fidelity, outperforming traditional methods in challenging scenarios.

Text-only models can rival multimodal counterparts in chest radiography accuracy, questioning the necessity of image input for clinical AI applications.

Ditch phoneme-based speech processing: directly predicting phonological features from speech unlocks substantial gains in multilingual and cross-lingual speech recognition.

Scaling clinical LLMs doesn't guarantee safety: high-risk errors persist even with advanced RAG and max-context prompting, highlighting the critical role of evidence quality and deployment strategy.

Achieve state-of-the-art 3D medical image generation by reformulating deterministic prediction as a multi-objective drifting problem, outperforming GANs, flow-matching, and SDEs in fidelity, realism, and efficiency.

Achieve state-of-the-art zero-shot chest X-ray classification by cleverly curating training data and distilling knowledge into CLIP models, sidestepping the need for large-scale retraining.