Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2501. 01908v4 Announce Type: replace-cross Abstract: Deep learning (DL) methods have become the state-of-the-art for reconstructing sub-sampled magnetic resonance imaging (MRI) data.
arXiv:2509. 22888v2 Announce Type: replace Abstract: Standard LLM evaluation practices compress diverse abilities into single scores, obscuring their inherently multidimensional nature.
arXiv:2606. 16278v1 Announce Type: cross Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale.
arXiv:2606. 16127v1 Announce Type: cross Abstract: The worldwide surge of authoritarianism, combined with the increasing central role in users' everyday lives, raises the question of to what extent specific models exhibit or promote authoritarian attitudes and characteristics.
arXiv:2606. 15821v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages.
arXiv:2606. 14954v1 Announce Type: cross Abstract: We develop a general framework for analyzing representation costs of parametric data-fitting methods through their parameter-space regularizers.
arXiv:2606. 16428v1 Announce Type: cross Abstract: Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners.
arXiv:2606. 16626v1 Announce Type: cross Abstract: Based on a questionnaire of 100 higher-education students, predominantly from engineering-related fields, and a critical review of recent literature, this chapter examines how students use and perceive Large Language Models (LLMs) in engineering education.
arXiv:2606. 14752v1 Announce Type: cross Abstract: Modern Vision-Language-Action (VLA) models must bridge pretrained vision-language reasoning and precise continuous robot control.
arXiv:2605. 28734v2 Announce Type: replace-cross Abstract: A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written.
arXiv:2606. 16511v1 Announce Type: new Abstract: Recent work motivates moving large language model (LLM) evaluation from mean-based to tail-aware metrics, including conditional value-at-risk and tail-index estimates of reward-model error.
arXiv:2606. 15115v1 Announce Type: new Abstract: Multi-objective optimization (MOO) has emerged as a powerful approach to solving complex optimization problems involving multiple objectives.
arXiv:2606. 15369v1 Announce Type: new Abstract: We study repeated bilateral trade from a fairness perspective.
arXiv:2603. 10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning.
arXiv:2606. 15077v1 Announce Type: new Abstract: We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries.
arXiv:2606. 15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive.
arXiv:2602. 05060v2 Announce Type: replace Abstract: Cybergrooming is an evolving threat to youth, requiring proactive educational interventions.
arXiv:2602. 17997v3 Announce Type: replace Abstract: Animals perform coordinated whole-body movements under the control of neural systems shaped by brain-wide connectivity.
arXiv:2606. 16891v1 Announce Type: cross Abstract: Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to capture the full scope of modern payloads like synthetic data and federated analytics.
arXiv:2606. 15708v1 Announce Type: new Abstract: Welcome to the ninth edition of the AI Index report.