Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 07533v2 Announce Type: replace Abstract: Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models.
arXiv:2606. 26346v1 Announce Type: new Abstract: Agentic benchmarks have emerged across general-purpose and domain-specific settings, including finance, coding, law, and drug discovery, yet energy-domain evaluations remain largely limited to static knowledge recall.
arXiv:2606. 26918v1 Announce Type: new Abstract: Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak.
arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.
arXiv:2606. 26575v1 Announce Type: cross Abstract: Complex multi-agent control tasks remain challenging for traditional rule-based and model-based approaches, motivating the adoption of learning-based methods.
arXiv:2606. 26451v1 Announce Type: cross Abstract: Automatic singing quality assessment (SQA) requires evaluating lyrical correctness and musical fidelity while handling expressive variations.
arXiv:2606. 27147v1 Announce Type: cross Abstract: Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens.
arXiv:2606. 26200v1 Announce Type: cross Abstract: Modern machine learning systems have outgrown their origins as isolated predictive constructs, evolving into complex socio-technical architectures that actively mediate human opportunity.
arXiv:2606. 26990v1 Announce Type: cross Abstract: Uncertainty estimates in machine learning are typically evaluated using generic metrics such as the negative log-likelihood and expected calibration error, yet good performance on such metrics does not necessarily imply high utility in downstream decisions.
arXiv:2606. 26795v1 Announce Type: cross Abstract: Video Diffusion Models (VDMs) is constrained by immense computational costs.
arXiv:2606. 26228v1 Announce Type: cross Abstract: We review the concepts of interpretability and explainability as they apply to machine learning in physics.
arXiv:2606. 26455v1 Announce Type: cross Abstract: RGB-Event tracking improves localization robustness by fusing RGB appearance textures and dense temporal motion cues from event sensors.
arXiv:2606. 27023v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) applied to Medical Visual Question Answering (VQA) tend to produce overconfident outputs regardless of actual correctness, and existing verbalized confidence calibration methods, developed primarily for text only LLMs, do not account for the multimodal nature of medical image understanding.
arXiv:2606. 26922v1 Announce Type: cross Abstract: Continuous driver monitoring in automated vehicles requires low-latency inference while avoiding unsafe decisions under uncertain driver states.
arXiv:2606. 26523v1 Announce Type: new Abstract: We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.
arXiv:2606. 26317v1 Announce Type: cross Abstract: Accurate fault diagnosis of rolling element bearings in rotating machinery is considered essential for ensuring industrial safety and enabling predictive maintenance.
arXiv:2606. 26617v1 Announce Type: new Abstract: Scaling laws describe how learning performance varies with model size, data size, and compute.
arXiv:2606. 26933v1 Announce Type: cross Abstract: AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and efficiently filters false positives.
arXiv:2606. 27302v1 Announce Type: cross Abstract: AI healthcare chatbots are increasingly used to support health information seeking and self-management, yet their performance and impact on users remains to be studied.
arXiv:2606. 26794v1 Announce Type: cross Abstract: CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment.