Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 27154v1 Announce Type: cross Abstract: CT vision-language foundation models have demonstrated promising performance across downstream tasks, but are typically trained with whole-volume representations that dilute fine-grained anatomical signals.
arXiv:2605. 05905v2 Announce Type: replace Abstract: Objective perturbation is a standard mechanism in differentially private empirical risk minimization.
arXiv:2607. 27905v1 Announce Type: new Abstract: Counterfactual explanations (CFEs) enhance the interpretability of black-box models by generating alternative instances with adjusted feature values that achieve a contrastive outcome.
arXiv:2506. 23033v5 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment.
arXiv:2511. 12449v3 Announce Type: replace-cross Abstract: Recent Multimodal Large Language Models (MLLMs) have significantly advanced e-commerce product understanding.
arXiv:2607. 26621v2 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs).
arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).
arXiv:2607. 28608v1 Announce Type: new Abstract: Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups.
arXiv:2607. 26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate.
arXiv:2607. 26641v1 Announce Type: cross Abstract: Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns.
arXiv:2607. 26645v1 Announce Type: cross Abstract: Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion.
arXiv:2607. 26723v1 Announce Type: cross Abstract: Inversion-based watermarking is a promising approach to authenticate diffusion-generated images, yet practical use is bottlenecked by inversion that is both slow and error-prone.
arXiv:2607. 27656v1 Announce Type: new Abstract: Looped Transformers create a useful train- and test-time compute axis by reusing the same Transformer block over recurrent depth, increasing effective depth at a fixed parameter count.
arXiv:2607. 26914v1 Announce Type: cross Abstract: Biomedical laboratory robots must navigate to instruments before performing experimental procedures.
arXiv:2607. 26947v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cross-modal understanding.
arXiv:2607. 26317v1 Announce Type: cross Abstract: Psychometric calibration for educational tests typically requires costly human response data.
arXiv:2607. 27066v1 Announce Type: cross Abstract: Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support the manuscript's claims, and communicate evidence with a clear visual hierarchy.
arXiv:2607. 27084v1 Announce Type: cross Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers.
arXiv:2607. 27594v1 Announce Type: new Abstract: Post-training alignment in large reasoning models (LRMs) has significantly improved their adaptability to diverse safety compliance settings.
arXiv:2607. 27507v1 Announce Type: new Abstract: Matrix factorisation is a fundamental tool for exploiting low-dimensional structure in high-dimensional data, with applications such as data compression, denoising, structure discovery, interpretable representation learning, and dimensionality reduction.