Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2412. 05894v2 Announce Type: replace-cross Abstract: Federated learning (FL) enables collaborative analysis of biomedical data without exchanging sensitive patient-level information, but its performance in multi-center studies may be compromised by batch effects which can obscure biological signals.
arXiv:2604. 03329v2 Announce Type: replace-cross Abstract: Automatic violence detection from video is challenging because violent interactions may be distant, occluded, or only partially visible.
arXiv:2602. 14401v2 Announce Type: replace-cross Abstract: Vision-Language Navigation VLN requires large-scale trajectory instruction data from private indoor environments, raising significant privacy concerns.
arXiv:2603. 07606v2 Announce Type: replace Abstract: Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust.
arXiv:2607. 03050v1 Announce Type: cross Abstract: Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost.
arXiv:2605. 17758v2 Announce Type: replace Abstract: Synthetic data is widely used in healthcare to create datasets that preserve statistical properties of real data without exposing sensitive patient information.
arXiv:2607. 05163v1 Announce Type: cross Abstract: AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate.
arXiv:2607. 03640v1 Announce Type: cross Abstract: Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic.
arXiv:2607. 05198v1 Announce Type: cross Abstract: Minimum Bayes Risk (MBR) decoding yields more robust and higher-quality text generation than maximum a posteriori (MAP) decoding by selecting hypotheses that maximize expected utility over sampled pseudo-references.
arXiv:2509. 23960v2 Announce Type: replace-cross Abstract: Co-optimizing safety and performance in large-scale multi-agent systems remains a fundamental challenge.
arXiv:2506. 23845v2 Announce Type: replace-cross Abstract: While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness.
arXiv:2605. 20494v2 Announce Type: replace Abstract: Reliable assessment of tropical cyclone risk is limited by the short and spatially uneven historical record, especially for rare, high-intensity landfalls that dominate insured loss.
arXiv:2607. 04293v1 Announce Type: cross Abstract: Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention.
arXiv:2607. 05187v1 Announce Type: new Abstract: As CMOS technology scales into the deep nanometer regime, digital circuit reliability is increasingly threatened by the combined stochastic effects of Bias Temperature Instability (BTI) and Process Variation (PV).
arXiv:2607. 03126v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has substantially improved the reasoning ability of large language models (LLMs), but sparse outcome rewards still make token-level credit assignment difficult.
arXiv:2607. 04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks.
arXiv:2509. 22082v3 Announce Type: replace Abstract: Federated learning enables distributed information sharing and collaborative model training without exposing raw client data.
arXiv:2607. 03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cyber investigation.
arXiv:2607. 02990v1 Announce Type: new Abstract: We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning node and graph embeddings from large, heterogeneous graphs, demonstrated here on geospatial mineral-exploration data.
arXiv:2607. 05188v1 Announce Type: new Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on.