Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 16210v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a major barrier to deployment.
arXiv:2607. 16620v1 Announce Type: cross Abstract: Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems.
arXiv:2607. 16938v1 Announce Type: cross Abstract: End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation.
arXiv:2607. 16351v1 Announce Type: cross Abstract: Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release.
arXiv:2511. 03826v4 Announce Type: replace-cross Abstract: Accurate and efficient registration of whole slide images (WSIs) is essential for high-resolution, nuclei-level analysis in multi-stained tissue slides.
arXiv:2511. 07457v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks.
arXiv:2512. 04124v4 Announce Type: replace-cross Abstract: Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear.
arXiv:2607. 18034v1 Announce Type: new Abstract: Smart home assistants interpret a wide range of user commands, from explicit device control to underspecified and preference dependent requests.
arXiv:2607. 17266v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing.
arXiv:2604. 20288v2 Announce Type: replace Abstract: Flight diversions are rare but high-impact events in aviation, making their reliable prediction vital for both safety and operational efficiency.
arXiv:2607. 17946v1 Announce Type: cross Abstract: Large Language Models (LLMs) often struggle to navigate value conflicts when trained with the compressed scalar rewards of Reinforcement Learning from Human Feedback (RLHF).
arXiv:2607. 16868v1 Announce Type: new Abstract: Large Language Models (LLMs) often produce confidently stated yet unreliable outputs, posing critical challenges for deployment in safety-sensitive applications.
arXiv:2511. 14592v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns.
arXiv:2602. 00387v4 Announce Type: replace-cross Abstract: Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors.
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.
arXiv:2607. 16208v1 Announce Type: new Abstract: Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment.
arXiv:2603. 22590v2 Announce Type: replace Abstract: With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become highly relevant.
arXiv:2607. 16969v1 Announce Type: new Abstract: Predictive maintenance relies on accurate Remaining Useful Life estimation, often formulated using survival analysis over multivariate time-series data.
arXiv:2607. 16222v1 Announce Type: cross Abstract: This paper presents ARGO, a smart eyewear platform designed to bridge ergonomic comfort, high computational throughput, and energy efficiency.
arXiv:2510. 19244v3 Announce Type: replace Abstract: Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior.