Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 31282v1 Announce Type: new Abstract: Modern deep neural networks often contain far more parameters than needed to fit their training data, yet they achieve impressive generalization.
arXiv:2601. 16398v3 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators.
arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.
arXiv:2606. 31963v1 Announce Type: new Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments.
arXiv:2606. 31635v1 Announce Type: cross Abstract: Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic.
arXiv:2404. 01356v4 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
arXiv:2603. 29759v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment.
arXiv:2606. 31876v1 Announce Type: new Abstract: To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space.
arXiv:2312. 00305v3 Announce Type: replace-cross Abstract: Many important tasks of large-scale recommender systems can be naturally cast as testing multiple linear forms for noisy matrix completion.
arXiv:2606. 31126v1 Announce Type: new Abstract: Predicting biomolecular properties from limited labeled data is a central bottleneck in protein engineering and small-molecule design.
arXiv:2606. 32027v1 Announce Type: cross Abstract: Reward design remains a central bottleneck for autonomous robot policy improvement, especially in long-horizon manipulation tasks where sparse success labels provide too little signal and binary preferences collapse many competing notions of quality into one ambiguous signal.
arXiv:2606. 31253v1 Announce Type: cross Abstract: The classical $k$-means clustering, based on distances computed from all data features, cannot be directly applied to incomplete data with missing values.
arXiv:2606. 31984v1 Announce Type: cross Abstract: Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the final re-ranking step disproportionately shapes user engagement and downstream performance, particularly for carousel and grid display formats.
arXiv:2606. 31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts.
arXiv:2606. 31742v1 Announce Type: cross Abstract: Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep learning model decisions, enhancing interpretability for users.
arXiv:2606. 31594v1 Announce Type: cross Abstract: The Internet of Things (IoT) is rapidly growing and expanding into various sectors, such as healthcare, transportation, smart homes, and more.
arXiv:2606. 30899v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious behavior when a hidden trigger is present.
arXiv:2606. 30780v1 Announce Type: cross Abstract: Audio deepfakes are a growing challenge for the general public, as well as for journalists and fact-checkers.
arXiv:2603. 16436v2 Announce Type: replace Abstract: Counterfactual explanations (CE) explain model decisions by identifying input modifications that lead to different predictions.
arXiv:2605. 16399v2 Announce Type: replace-cross Abstract: The inversion of diffusion models plays a central role in image editing.