Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 28672v1 Announce Type: cross Abstract: When a neural network predicts a physical system accurately, has it learned the governing law as formal, structured knowledge, and if so, does the network's internal computation actually use that representation throughout the law's domain of validity?
arXiv:2607. 27690v2 Announce Type: replace-cross Abstract: We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience.
arXiv:2604. 05150v2 Announce Type: replace-cross Abstract: We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation.
arXiv:2607. 28680v1 Announce Type: cross Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities.
arXiv:2607. 28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning.
arXiv:2607. 29456v1 Announce Type: cross Abstract: Double Machine Learning (DML) is a popular approach for treatment effect estimation in various settings, which allows a wide range of flexible machine learning methods to be used for nuisance parameter estimation while preserving valid inference.
arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
arXiv:2607. 28630v1 Announce Type: cross Abstract: Generative AI (GenAI) holds significant promise for advancing educational equity among ethnic minority students by broadening access to learning resources and mitigating linguistic barriers.
arXiv:2607. 29431v1 Announce Type: new Abstract: Large language models increasingly generate optimization models from natural language, but existing evaluation often reduces a generated model and its ground truth to a single equivalent/not-equivalent verdict or an execution-success rate--labels that are neither independently checkable nor faithful to the multiple distinct senses in which two formulations can agree.
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
arXiv:2605. 29975v2 Announce Type: replace Abstract: We present a fully convolutional denoising autoencoder (FC-DAE) tailored for two-dimensional representations of dynamic correlations that is applicable to many experimental techniques.
arXiv:2607. 29441v1 Announce Type: new Abstract: Many real-world systems rely on predictive models to inform decisions, and fairness concerns arise in both the prediction and decision stages.
arXiv:2607. 28687v1 Announce Type: cross Abstract: As populations age, cognitive decline from mild cognitive impairment (MCI) to dementia is a defining health challenge of the coming decades, yet routine assessment often misses its earliest signs.
arXiv:2607. 28959v1 Announce Type: cross Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs).
arXiv:2602. 02685v3 Announce Type: replace Abstract: Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions.
arXiv:2607. 29240v1 Announce Type: cross Abstract: In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypical state.
arXiv:2607. 29624v1 Announce Type: cross Abstract: Traditional static assessments rely on a subtractive, deficit-based grading model that often penalizes ambition and obscures diagnostic feedback.
arXiv:2607. 29283v1 Announce Type: cross Abstract: Training large language models (LLMs) to write register-transfer level (RTL) requires large corpora of paired specifications and code, and such data is scarce enough that most public corpora are now synthesized.