DualShield: Safe Model Predictive Diffusion via Reachability Analysis for Interactive Autonomous Driving
arXiv:2601.15729v1 Announce Type: cross Abstract: Diffusion models have emerged as a powerful approach for multimodal motion planning in autonomous driving.…
Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
arXiv:2601.14758v2 Announce Type: replace-cross Abstract: Post-training pretrained Autoregressive models (ARMs) into Masked Diffusion models (MDMs) has emerged as a cost-effective…
The Ontological Neutrality Theorem: Why Neutral Ontological Substrates Must Be Pre-Causal and Pre-Normative
arXiv:2601.14271v1 Announce Type: new Abstract: Modern data systems must support accountability across persistent legal, political, and analytic disagreement. This requirement…
RL-BioAug: Label-Efficient Reinforcement Learning for Self-Supervised EEG Representation Learning
arXiv:2601.13964v2 Announce Type: replace-cross Abstract: The quality of data augmentation serves as a critical determinant for the performance of contrastive…
Auditing Language Model Unlearning via Information Decomposition
arXiv:2601.15111v1 Announce Type: cross Abstract: We expose a critical limitation in current approaches to machine unlearning in language models: despite…
An Agentic Operationalization of DISARM for FIMI Investigation on Social Media
arXiv:2601.15109v1 Announce Type: cross Abstract: The interoperability of data and intelligence across allied partners and their respective end-user groups is…
Performance and Complexity Trade-off Optimization of Speech Models During Training
arXiv:2601.13704v2 Announce Type: replace-cross Abstract: In speech machine learning, neural network models are typically designed by choosing an architecture with…