Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 04469v1 Announce Type: cross Abstract: We introduce Adaptive Calibration (AC), a novel calibration strategy for facial recognition that maps cosine similarity between normalized embeddings to well-calibrated probabilities.
arXiv:2602. 02834v4 Announce Type: replace-cross Abstract: What structural inductive bias helps transformers reason over knowledge graphs?
arXiv:2602. 01658v2 Announce Type: replace-cross Abstract: Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive comparisons.
arXiv:2602. 23214v2 Announce Type: replace-cross Abstract: Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors.
arXiv:2605. 29076v2 Announce Type: replace-cross Abstract: LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable instructions but struggles with performance and scalability.
arXiv:2605. 16331v2 Announce Type: replace-cross Abstract: Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biological evidence or retrieval of a statistical default.
arXiv:2604. 14575v2 Announce Type: replace-cross Abstract: Large language models enable inexpensive AI-generated annotations, but using them reliably for causal inference remains challenging.
arXiv:2509. 05510v3 Announce Type: replace-cross Abstract: Continued progress in inertial confinement fusion (ICF) requires solving inverse problems relating experimental observations to simulation input parameters, followed by design optimization.
arXiv:2605. 09081v4 Announce Type: replace-cross Abstract: We introduce the first universal pretraining corpus for industrial time-series data: FactoryNet.
arXiv:2004. 10846v5 Announce Type: replace-cross Abstract: Problem definition: Traditionally, New York City's top 8 public schools have selected candidates solely based on their scores in the Specialized High School Admissions Test (SHSAT).
arXiv:2605. 18879v3 Announce Type: replace-cross Abstract: Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety.
arXiv:2605. 24782v2 Announce Type: replace Abstract: While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution accuracy a poor proxy for scientific utility.
arXiv:2606. 04435v1 Announce Type: new Abstract: Multi-step agentic retrieval-augmented generation (RAG) pipelines have demonstrated significant capability for complex reasoning tasks, yet remain vulnerable to a class of failure that existing hallucination detection mechanisms systematically miss: cascading hallucination, where errors introduced at early pipeline stages propagate and amplify across successive reasoning steps, producing confident but factually incorrect final outputs.
arXiv:2606. 05149v1 Announce Type: cross Abstract: Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-relevant categories from naturalistic roadway video do not exist in the open literature.
arXiv:2605. 21446v2 Announce Type: replace-cross Abstract: Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation.
arXiv:2606. 04797v1 Announce Type: cross Abstract: Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts.
arXiv:2604. 25860v2 Announce Type: replace-cross Abstract: Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints.
arXiv:2512. 03553v3 Announce Type: replace-cross Abstract: Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environments where moderation must be timely, multimodal, and robust to evolving forms of unwanted content.
arXiv:2601. 06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations.
arXiv:2606. 04380v1 Announce Type: cross Abstract: Forecast reconciliation usually starts from a fixed measurement system and asks how forecasts should be projected onto a coherent space.