Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 11947v1 Announce Type: cross Abstract: Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, which makes them unreliable measures of model knowledge.
arXiv:2608. 11815v1 Announce Type: new Abstract: Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models.
arXiv:2608. 12194v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) enhance nonlinear function approximation by replacing scalar weights with learnable univariate functions.
arXiv:2608. 11354v1 Announce Type: new Abstract: Modern recommender systems treat observed actions as reliable proxies for user preferences, yet interactions often reflect exploration or comparison rather than stable preference expression.
arXiv:2510. 21112v3 Announce Type: replace-cross Abstract: High-definition 3D city maps enable city planning and change detection, which is essential for municipal compliance, map maintenance, and asset monitoring, including both built structures and urban greenery.
arXiv:2506. 17332v2 Announce Type: replace-cross Abstract: By 2050, people aged 65 and over are projected to make up 16% of the global population.
arXiv:2608. 11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.
arXiv:2608. 11241v1 Announce Type: new Abstract: Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (schema-conforming feature extraction, non-crashing A/B, zero compliance-path hallucination), and end-to-end efficiency.
arXiv:2608. 11224v1 Announce Type: new Abstract: Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or experiments, and judgement that links a new question to an old result.
arXiv:2608. 04201v2 Announce Type: replace Abstract: Nonlinear state estimation requires sequentially fusing model-based predictions with noisy measurements.
arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.
arXiv:2608. 11493v1 Announce Type: new Abstract: Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale.
arXiv:2608. 11244v1 Announce Type: new Abstract: Construction standards are critical for building safety and sustainability.
arXiv:2507. 15100v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) determines whether a premise entails, contradicts, or is neutral with respect to a hypothesis.
arXiv:2608. 11283v1 Announce Type: cross Abstract: Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity.
arXiv:2608. 11909v1 Announce Type: new Abstract: Two accounts recur in explanations of the success of rotary position embeddings (RoPE).
arXiv:2608. 12231v1 Announce Type: new Abstract: We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items.
arXiv:2507. 22423v3 Announce Type: replace Abstract: To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently general to encompass diverse paradigms of intelligent behavior, including reinforcement learning, generative models, classification, analogical reasoning, and goal-directed decision-making.
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv:2608. 12236v1 Announce Type: cross Abstract: We study how organizations use frontier generative AI by linking ChatGPT Enterprise account records to usage, worker roles, task classifications, and public-company financial data through March 2026.