Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 16742v1 Announce Type: cross Abstract: With the rapid advancement of video generation models, distinguishing between AI-generated and authentic videos has emerged as a challenging endeavor.
arXiv:2606. 16878v1 Announce Type: new Abstract: Retail marketing measurement increasingly requires granular campaign-level insights without relying on user-level tracking.
arXiv:2606. 14817v1 Announce Type: cross Abstract: This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG).
arXiv:2606. 16313v1 Announce Type: cross Abstract: Long-tail scenarios remain a major bottleneck for autonomous driving evaluation, even as datasets grow by orders of magnitude.
arXiv:2606. 15250v1 Announce Type: cross Abstract: Radiographic assessment of lower-limb alignment (LLA) is important for predicting joint health and surgical outcomes in total knee arthroplasty.
arXiv:2606. 15280v1 Announce Type: new Abstract: Most existing anomaly detection methods rely on estimating a probability density or learning an enclosing decision boundary, implicitly assuming that normal data occupies a region of non-zero volume in the ambient space.
arXiv:2606. 16003v1 Announce Type: new Abstract: This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts.
arXiv:2606. 16364v1 Announce Type: new Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness.
arXiv:2604. 22119v2 Announce Type: replace Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs).
arXiv:2606. 16999v1 Announce Type: cross Abstract: Frozen small code models ( =45.
arXiv:2606. 15335v1 Announce Type: cross Abstract: When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as formatting conventions, vocabulary choices, and syntactic patterns.
arXiv:2606. 16180v1 Announce Type: cross Abstract: With new data privacy laws such as the General Data Protection Regulation (GDPR) [1] that allow individuals to ask that any of their personal information be erased from trained machine learning models, there has been a push to investigate the unlearning of data from models as a way to comply with these laws.
arXiv:2504. 11320v4 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day.
arXiv:2606. 15284v1 Announce Type: cross Abstract: Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support.
arXiv:2606. 15314v1 Announce Type: cross Abstract: Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take.
arXiv:2606. 15396v1 Announce Type: cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.
arXiv:2605. 27284v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed.
arXiv:2606. 15419v1 Announce Type: cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA).
arXiv:2606. 15980v1 Announce Type: cross Abstract: Activation monitors-lightweight probes trained on a language model's internal representations-are an increasingly common layer in deployment safety stacks.
arXiv:2606. 15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive.