Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 05187v1 Announce Type: cross Abstract: Among the many challenges hindering the responsible development and deployment of AI, arguably none has faced more intense scrutiny than bias in its various forms.
arXiv:2606. 05395v1 Announce Type: cross Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior.
arXiv:2606. 05843v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract query-relevant visual features from complex, noisy contexts remain opaque.
arXiv:2606. 05389v1 Announce Type: new Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations.
arXiv:2603. 20990v2 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation.
arXiv:2606. 06223v1 Announce Type: new Abstract: Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal model state and environment context.
arXiv:2503. 14295v3 Announce Type: replace-cross Abstract: Recent advancements in audio-driven talking face generation have made great progress in lip synchronization.
arXiv:2510. 00054v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks.
arXiv:2606. 06219v1 Announce Type: cross Abstract: End-to-end autonomous driving models often struggle to balance multi-modal maneuver generation with real-time inference constraints.
arXiv:2606. 06109v1 Announce Type: cross Abstract: Entity alignment (EA) aims to identify equivalent entities across heterogeneous knowledge graphs (KGs) and is a key component of knowledge fusion and cross-KG reasoning.
arXiv:2606. 05901v1 Announce Type: cross Abstract: Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing.
arXiv:2606. 05710v1 Announce Type: cross Abstract: The increasing penetrations of the critical infrastructure sector in the United States with intelligent digital technologies have greatly increased exposure to advanced cyber adversaries and operational vulnerabilities.
arXiv:2606. 05563v1 Announce Type: new Abstract: Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context.
arXiv:2605. 15212v2 Announce Type: replace-cross Abstract: We propose a new numerical method to estimate the fault tolerance of failure modes in digital circuit structures with a generative network sampling technique.
arXiv:2606. 05966v1 Announce Type: cross Abstract: Understanding and reasoning about the physical world is the foundation of intelligent behavior, yet state-of-the-art vision-language models (VLMs) still fail at causal physical reasoning, often producing plausible but incorrect answers.
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
arXiv:2606. 05779v1 Announce Type: cross Abstract: Autonomous spacecraft require rapid, lightweight, and reliable onboard detection of cyber-RF threats.
arXiv:2606. 05734v1 Announce Type: new Abstract: Large language models (LLMs) are generally constrained from expressing feelings through human-preference alignment in post-training processes.
arXiv:2606. 05740v1 Announce Type: new Abstract: Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias.
arXiv:2606. 05660v1 Announce Type: cross Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments.