77 citations · 79 across the 7 of their papers we have counts for
8 papers
Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining
Lukas Thede, Shengzhuang Chen, Stefan Winzeck +3
Continued pretraining enables language models to adapt to new domains and knowledge, but often at the cost of forgetting previously acquired capabilities. Replay can mitigate this…
Thomson: Continual Learning of Frontier Models for SovereignAI
Shengzhuang Chen, Jerrod Parker, Yejin Bang +23
The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information, economic and power asymmetr…
Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models
John Scoville, Shengzhuang Chen, Yejin Bang +2
Recent meta-reasoning frameworks improve LLM reasoning by wrapping chain-of-thought generation in an iterative control loop, allowing more effective backtracking, termination of re…
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
Lukas Thede, Stefan Winzeck, Zeynep Akata +1
Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known…
Risk of Bias in Chest Radiography Deep Learning Foundation Models
Ben Glocker, Charles Jones, Melanie Roschewitz +1
Purpose: To analyze a recently published chest radiography foundation model for the presence of biases that could lead to subgroup performance disparities across biological sex and…
Algorithmic encoding of protected characteristics in image-based models for disease detection
Ben Glocker, Charles Jones, Melanie Bernhardt +1
It has been rightfully emphasized that the use of AI for clinical decision making could amplify health disparities. An algorithm may encode protected characteristics, and then use…
Transductive image segmentation: Self-training and effect of uncertainty estimation
Konstantinos Kamnitsas, Stefan Winzeck, Evgenios N. Kornaropoulos +9
Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model…
Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification
Talha Qaiser, Stefan Winzeck, Theodore Barfoot +9
Whole body magnetic resonance imaging (WB-MRI) is the recommended modality for diagnosis of multiple myeloma (MM). WB-MRI is used to detect sites of disease across the entire skele…