Leveraging Analytic Gradients in Provably Safe Reinforcement Learning
arXiv:2506.01665v2 Announce Type: replace-cross Abstract: The deployment of autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning…
Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulation
arXiv:2507.19368v1 Announce Type: cross Abstract: Artificial intelligence is increasingly leveraged across various domains to automate decision-making processes that significantly impact…
Latent Space Analysis for Melanoma Prevention
arXiv:2506.18414v2 Announce Type: replace-cross Abstract: Melanoma represents a critical health risk due to its aggressive progression and high mortality, underscoring…
Deepfake Detection Via Facial Feature Extraction and Modeling
arXiv:2507.18815v1 Announce Type: cross Abstract: The rise of deepfake technology brings forth new questions about the authenticity of various forms…
Data Augmentation for Spoken Grammatical Error Correction
arXiv:2507.19374v1 Announce Type: cross Abstract: While there exist strong benchmark datasets for grammatical error correction (GEC), high-quality annotated spoken datasets…
Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
arXiv:2503.05996v2 Announce Type: replace-cross Abstract: Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn…