Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 23934v1 Announce Type: new Abstract: Machine unlearning, which aims to remove the influence of specific training data from a trained model, is a key requirement for privacy, accountability, and adaptive deployment.
arXiv:2607. 23236v1 Announce Type: cross Abstract: Federated learning has achieved considerable success for predictive modelling, yet federated descriptive analytics remains largely unexplored.
arXiv:2607. 24177v1 Announce Type: cross Abstract: Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against content-injection attacks; and (iv) neglect the computational requirements for deployment, risking slow inference on endpoints.
arXiv:2407. 14766v4 Announce Type: replace-cross Abstract: This paper presents a philosophical and experimental study of fairness interventions in AI classification, centered on the explainability and transparency of corrective methods, and on the opposition between two fairness criteria, namely Demographic Parity and Equalized Odds.
arXiv:2411. 00839v4 Announce Type: replace-cross Abstract: Deep learning has led to tremendous success in computer vision, largely due to Convolutional Neural Networks (CNNs).
arXiv:2502. 05925v2 Announce Type: replace-cross Abstract: Backpropagation (BP) has long been the predominant method for training neural networks due to its effectiveness.
arXiv:2509. 24770v2 Announce Type: replace Abstract: Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations.
arXiv:2607. 22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem.
arXiv:2604. 11151v2 Announce Type: replace Abstract: We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$.
arXiv:2605. 14981v2 Announce Type: replace Abstract: Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system.
arXiv:2607. 23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.
arXiv:2607. 23991v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements.
arXiv:2607. 22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk.
arXiv:2607. 23802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization.
arXiv:2607. 24336v1 Announce Type: new Abstract: City-scale autonomous vehicle fleet coordinators are typically optimized for aggregate travel time, yet fleet averages conceal how delay is distributed across trips and regions.
arXiv:2607. 22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data.
arXiv:2607. 22566v1 Announce Type: new Abstract: MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue.
arXiv:2607. 23289v1 Announce Type: cross Abstract: Gene regulatory network modeling often requires balancing predictive accuracy and mechanistic interpretability.
arXiv:2607. 22716v1 Announce Type: cross Abstract: In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations.
arXiv:2607. 23361v1 Announce Type: cross Abstract: Language generation in the limit is an elegant model introduced by Kleinberg and Mullainathan [KM24] to formally study language generation by an algorithm that learns solely based on example strings.