Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.00767v1 Announce Type: cross Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later trai...
arXiv:2610.00861v1 Announce Type: cross Abstract: Adversarial optimization under a shared $\ell_1$ budget requires deciding not only how much perturbation to use, but also where that limited budget s...
arXiv:2610.01028v1 Announce Type: cross Abstract: Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely...
arXiv:2610.01168v1 Announce Type: cross Abstract: Time Series Anomaly Detection has received increasing attention, driven by the growing availability of complex time series data. This surge has led t...
arXiv:2610.01223v1 Announce Type: cross Abstract: Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as th...
arXiv:2610.01284v1 Announce Type: cross Abstract: Model validation estimates the performance of a complete learning procedure on new data. However, an invalid split can produce an optimistic and stab...
arXiv:2610.01515v1 Announce Type: cross Abstract: Adaptive preconditioners accelerate model training, but heterogeneous client geometries can bias federated updates even when gradients are evaluated...
arXiv:2610.01789v1 Announce Type: cross Abstract: Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion...
arXiv:2610.02186v1 Announce Type: cross Abstract: Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitl...
arXiv:2610.00024v1 Announce Type: new Abstract: Across three vision-language model architectures (LLaVA-1.5-7B, Qwen2.5-VL-7B, InternVL3-8B), we report a universal negative finding for mid-layer inte...
arXiv:2610.00535v1 Announce Type: new Abstract: Uncertainty quantification is critical in scientific machine learning, where black-box, image-based models are increasingly deployed in high-stakes set...
arXiv:2610.00562v1 Announce Type: cross Abstract: Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient...
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive,...
arXiv:2610.00693v1 Announce Type: new Abstract: Federated learning (FL) has recently attracted increasing attention in remote sensing (RS) since it enables collaborative model training across decentr...
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamic...
arXiv:2610.00851v1 Announce Type: new Abstract: Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in O...
arXiv:2610.00922v1 Announce Type: new Abstract: Gaze estimation under natural head-eye motion underpins applications from driver monitoring to human-computer interaction. Single-frame methods predict...
arXiv:2610.01005v1 Announce Type: new Abstract: As artificial intelligence is increasingly deployed, algorithmic unfairness has raised growing concerns and intensified demands for transparent fairnes...
arXiv:2610.01408v1 Announce Type: new Abstract: Trajectory crossing remains a critical bottleneck in Flow Matching (FM), and previous works typically view these crossings from a theoretical optimizat...
arXiv:2610.01670v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-based image editing and as reward signals for model...