Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 05689v1 Announce Type: new Abstract: Understanding potential selection in data is crucial for causal discovery; we argue that "selection" in common narratives takes two forms, which we term static and evolutionary selection, respectively.
arXiv:2603. 25157v2 Announce Type: replace Abstract: Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond.
arXiv:2606. 06288v1 Announce Type: cross Abstract: Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements.
arXiv:2605. 10807v4 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor industry.
arXiv:2606. 05946v1 Announce Type: new Abstract: The rights to rectification and erasure, as established under the General Data Protection Regulation (GDPR), are central to protecting individuals' privacy.
arXiv:2606. 05860v1 Announce Type: new Abstract: Designing neural architectures for time-series forecasting and anomaly detection remains a resource-intensive task that often requires substantial domain expertise.
arXiv:2602. 01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors.
arXiv:2606. 06205v1 Announce Type: new Abstract: Continuous-time event data, in which entities emit instantaneous events over time, arises naturally across many domains such as neuroscience, seismology, and social networks.
arXiv:2606. 06010v1 Announce Type: new Abstract: Long-term time series forecasting benefits from inductive biases that expose recurring temporal structure.
arXiv:2606. 05345v1 Announce Type: new Abstract: We unify RoPE's Fourier phase, Jordan-RoPE's finite jets, and ALiBi's affine recency into a single learnable relative-position space, and study which regions of this space are selected by different tasks.
arXiv:2602. 05056v2 Announce Type: replace-cross Abstract: Online scams increasingly leverage fluent and context-aware social engineering strategies, creating growing demand for AI systems that explain why a message may be risky.
arXiv:2606. 06094v1 Announce Type: cross Abstract: Advances in computational modeling, neuroimaging, and artificial intelligence are revolutionizing the modeling of neurological disorders for improved diagnostics, prognosis, and treatment planning.
arXiv:2505. 05026v5 Announce Type: replace-cross Abstract: User interface (UI) design goes beyond visuals to shape user experience (UX), underscoring the shift toward UI/UX as a unified concept.
arXiv:2512. 14338v3 Announce Type: replace Abstract: Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data.
arXiv:2511. 16111v2 Announce Type: replace-cross Abstract: Graph spectral representations are fundamental in graph signal processing, providing a rigorous frameworkforanalyzing graph-structured data.
arXiv:2606. 06493v1 Announce Type: cross Abstract: For a humanoid robot to be deployed in the real world, the choice of command space (i.
arXiv:2606. 05551v1 Announce Type: cross Abstract: Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety guarantees.
arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.
arXiv:2605. 27292v2 Announce Type: replace Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters.
arXiv:2606. 05308v1 Announce Type: new Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set.