Pixel-level Certified Explanations via Randomized Smoothing
arXiv:2506.15499v1 Announce Type: cross Abstract: Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However,…
Contemporary AI foundation models increase biological weapons risk
arXiv:2506.13798v1 Announce Type: cross Abstract: The rapid advancement of artificial intelligence has raised concerns about its potential to facilitate biological…
Adjustment for Confounding using Pre-Trained Representations
arXiv:2506.14329v1 Announce Type: cross Abstract: There is growing interest in extending average treatment effect (ATE) estimation to incorporate non-tabular data,…
Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation
arXiv:2506.13628v2 Announce Type: replace-cross Abstract: Synthetic data generation plays a crucial role in medical research by mitigating privacy concerns and…
sHGCN: Simplified hyperbolic graph convolutional neural networks
arXiv:2506.14438v1 Announce Type: cross Abstract: Hyperbolic geometry has emerged as a powerful tool for modeling complex, structured data, particularly where…
Unifying Streaming and Non-streaming Zipformer-based ASR
arXiv:2506.14434v1 Announce Type: cross Abstract: There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models…
Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene
Nature Machine Intelligence, Published online: 18 June 2025; doi:10.1038/s42256-025-01040-8 Eye2Gene’s next-generation phenotyping of multimodal images increases diagnostic yield for inherited…