Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2510. 04927v2 Announce Type: replace-cross Abstract: Automatic modulation classification (AMC) is a core enabler of cognitive wireless systems, providing spectrum awareness and supporting adaptive communication at the network edge.
arXiv:2608. 16394v1 Announce Type: new Abstract: Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards.
arXiv:2608. 15762v1 Announce Type: cross Abstract: Container-granularity scheduling leaves abundant short-lived idle slices within containers unexploited.
arXiv:2608. 15715v1 Announce Type: cross Abstract: Quantum feedback control requires acting on noisy continuous measurement records without direct access to the underlying quantum state.
arXiv:2608. 16888v1 Announce Type: new Abstract: The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences.
arXiv:2608. 16773v1 Announce Type: new Abstract: Prototype-based neural networks are hailed as interpretable-by-design architectures.
arXiv:2608. 16259v1 Announce Type: cross Abstract: The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliable.
arXiv:2608. 15901v1 Announce Type: cross Abstract: Continual learning regularizers like EWC fight forgetting by penalizing changes from previous-task parameters with per-parameter importance, typically diagonal Fisher values.
arXiv:2608. 16237v1 Announce Type: cross Abstract: Building operations are energy-inefficient.
arXiv:2608. 16182v1 Announce Type: cross Abstract: Deep Q-learning (DQL) has achieved remarkable empirical success in reinforcement learning, yet its training process remains notoriously unstable.
arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.
arXiv:2608. 14963v1 Announce Type: cross Abstract: Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command.
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
arXiv:2608. 16338v1 Announce Type: cross Abstract: Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues.
arXiv:2608. 15929v1 Announce Type: new Abstract: Pedestrian path prediction is crucial for enhancing the safety of autonomous vehicles and advanced driver-assistance systems.
arXiv:2608. 15893v1 Announce Type: new Abstract: The rise of social media bots poses a persistent threat, enabling misinformation, opinion manipulation, and the erosion of trust in online platforms.
arXiv:2608. 15693v1 Announce Type: new Abstract: Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
arXiv:2608. 16380v1 Announce Type: cross Abstract: Monitoring war-induced damage to agricultural land in Ukraine is important for understanding threats to food security, environmental stability, and post-war recovery.
arXiv:2608. 15657v1 Announce Type: new Abstract: The rapid development and widespread application of artificial intelligence (AI) have sparked intense discussions on how to deploy responsible AI systems in a manner aligned with human values and ethical standards.