8 papers
Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews
André V. Duarte, Brian Tufts, Aditya Oke +3
How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not be attributed solely from the…
RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline
André V. Duarte, Xuying li, Bin Zeng +3
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself…
Deep Feedback Models
David Calhas, Arlindo L. Oliveira
Deep Feedback Models (DFMs) are a new class of stateful neural networks that combine bottom up input with high level representations over time. This feedback mechanism introduces d…
Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms
Joao D. S. Marques, Arlindo L. Oliveira
Pulmonary embolism is a leading cause of out of hospital cardiac arrest that requires fast diagnosis. While computed tomography pulmonary angiography is the standard diagnostic too…
Deep Recurrence for Dynamical Segmentation Models
David Calhas, Arlindo L. Oliveira
While biological vision systems rely heavily on feedback connections to iteratively refine perception, most artificial neural networks remain purely feedforward, processing input i…
DIS-CO: Discovering Copyrighted Content in VLMs Training Data
André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira +1
How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data? Motivated by the hypothesis that a V…