Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 03626v1 Announce Type: cross Abstract: Large language models are being integrated into critical infrastructure and enterprise workflows at unprecedented scale,yet the lifecycle frameworks governing their development and operations were designed for operational efficiency rather than security analysis.
arXiv:2608. 03588v1 Announce Type: cross Abstract: AI coding agents are stochastic workflows: prompts are interpreted, artifacts are sampled, validators produce observations, and orchestrators commit or repair.
arXiv:2608. 03659v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate scientific reviews, yet existing evaluations rarely examine whether different providers align with both conference decisions and human reviewing priorities within the same controlled setting.
arXiv:2608. 03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration.
arXiv:2606. 02965v2 Announce Type: replace Abstract: As large language models gain tool access and are deployed as autonomous agents capable of editing records, executing transactions, and modifying infrastructure, we still evaluate them based on the sole metric of task completion.
arXiv:2605. 28114v2 Announce Type: replace Abstract: Language-model agents are moving from single-user assistants into persistent networks that build trust and reputation with one another, and the same models increasingly control physically embodied robots as well as software.
arXiv:2407. 21311v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) aims to mitigate domain shift, where the distribution of labeled source data differs from that of unlabeled target data.
arXiv:2511. 09173v3 Announce Type: replace-cross Abstract: External trajectories can improve offline decision-sequence learning, but dynamics shift may make some source subsequences inconsistent with the target environment.
arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.
arXiv:2608. 00151v2 Announce Type: replace-cross Abstract: Current evaluation frameworks for artificial intelligence focus mainly on capability, safety, and proxies such as adoption, engagement, efficiency, productivity, and financial return.
arXiv:2608. 02877v1 Announce Type: new Abstract: Causal discovery recovers directed structure from observational data and is increasingly used in clinical settings to support mechanism reasoning and fairness audits of predictive models.
arXiv:2608. 03277v1 Announce Type: new Abstract: Differentially private zeroth-order optimization (DP-ZO) enables memory-efficient private fine-tuning of large language models using only forward evaluations.
arXiv:2608. 03927v1 Announce Type: new Abstract: Engineered Skeletal Muscle Tissues (ESMs) have become a key structure for biomedical disease modeling and pharmacological screening, yet their functional characterization often relies on simplistic metrics like peak force, discarding critical kinetic information.
arXiv:2510. 11834v3 Announce Type: replace Abstract: Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs.
arXiv:2608. 03892v1 Announce Type: new Abstract: We study linear representations of temporal horizon in the large language model Qwen3-32B and use them to change the model's time-related preferences, recommendations, and capabilities.
arXiv:2608. 03917v1 Announce Type: new Abstract: Causal perception occurs when agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, including the hypothetical distributions implied by each agent's SCM under the same set of interventions.
arXiv:2608. 03284v1 Announce Type: cross Abstract: Ensuring safety and policy compliance in text-to-image diffusion models remains a critical challenge, as benign or adversarial prompts can often elicit prohibited content, e.
arXiv:2608. 02991v1 Announce Type: new Abstract: Matrix spectral optimizers reshape weight-update spectra but usually delegate vector-valued biases to a separate optimizer.
arXiv:2608. 03190v1 Announce Type: new Abstract: Neuro-oncology decisions require coordinated interpretation of serial MRI, pathology, molecular markers, treatment history, performance status, and evolving guidelines.
arXiv:2608. 03569v1 Announce Type: new Abstract: Benchmarking the ability of AI scientists to generate novel ideas is notoriously difficult.