4 papers
System-Mediated Attention Imbalances Make Vision-Language Models Say Yes
Tsan Tsai Chan, Varsha Suresh, Anisha Saha +2
Vision-language model (VLM) hallucination is commonly linked to imbalanced allocation of attention across input modalities: system, image and text. However, existing mitigation str…
Systematicity between Forms and Meanings across Languages Supports Efficient Communication
Doreen Osmelak, Yang Xu, Michael Hahn +1
Languages vary widely in how meanings map to word forms. These mappings have been found to support efficient communication; however, this theory does not account for systematic rel…
Softmax Transformers are Turing-Complete
Hongjian Jiang, Michael Hahn, Georg Zetzsche +1
Hard attention Chain-of-Thought (CoT) transformers are known to be Turing-complete. However, it is an open problem whether softmax attention Chain-of-Thought (CoT) transformers are…
One Size Fits None: Rethinking Fairness in Medical AI
Roland Roller, Michael Hahn, Ajay Madhavan Ravichandran +10
Machine learning (ML) models are increasingly used to support clinical decision-making. However, real-world medical datasets are often noisy, incomplete, and imbalanced, leading to…