arXiv Machine Learning
Jul 22
Exposure-Based Reinforcement Learning to Rank
arXiv:2607. 18689v1 Announce Type: new Abstract: Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 22
Measuring Reward-Seeking via Contrastive Belief Updates
arXiv:2607. 18966v1 Announce Type: new Abstract: Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective.
arXiv AI
Jul 22
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
arXiv:2607. 19064v1 Announce Type: cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy.
arXiv AI
Jul 22
FSDBN: Foreground-Aware EEG--Visual Alignment via Dynamic Brain Networks
arXiv:2607. 18344v1 Announce Type: cross Abstract: EEG-based visual decoding provides a non-invasive pathway for interpreting visual semantics.
arXiv AI
Jul 22
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
arXiv AI
Jul 22
Breaking the Homogeneity Assumption: Specialized Multi-Generator Adversarial Learning for Rare Failure Detection in Predictive Maintenance
arXiv:2607. 19153v1 Announce Type: cross Abstract: Supervised learning models in the predictive maintenance field are regularly trained on highly imbalanced industrial datasets: machine failures occur rarely but have a disproportionate effect on operations.
arXiv AI
Jul 22
Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks
arXiv:2607. 18767v1 Announce Type: cross Abstract: The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability.
arXiv Machine Learning
Jul 22
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
arXiv:2508. 05157v2 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative training across distributed clients without sharing raw data, offering strong privacy benefits.
arXiv Machine Learning
Jul 22
The Tractability Landscape of Sampling with Inexact Scores
arXiv:2607. 19004v1 Announce Type: cross Abstract: We provide a simple and tight characterization of the types of inexact score oracle access that permit sampling with vanishing total variation bias, for a standard, well-behaved target family.
arXiv Machine Learning
Jul 22
Signed Rectified Flow: Negativity-Controlled Generation
arXiv:2607. 18516v1 Announce Type: new Abstract: We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $\pi^{sign} = (1+\alpha)\pi^+ - \alpha\pi^-$, where $\alpha>0$, $\pi^+$ is the distribution to promote, and $\pi^-$ is the distribution to suppress.
arXiv AI
Jul 22
ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
arXiv:2607. 19321v1 Announce Type: new Abstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted.
arXiv Machine Learning
Jul 22
Uncertainty Quantification for AI-Driven Crash Simulation Surrogates: A Comparative Study of Monte Carlo Dropout and Deep Ensemble on Open-Source Bumper Beam Benchmark
arXiv:2607. 18294v1 Announce Type: new Abstract: Machine learning surrogate models are increasingly being explored in engineering product development to augment simulation-driven design, offering near-instantaneous predictions that complement computationally expensive high-fidelity analyses.
arXiv AI
Jul 22
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
arXiv:2606. 25476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness.
arXiv AI
Jul 22
MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical Applications
arXiv:2409. 07314v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become saturated and increasingly disconnected from the functional requirements of clinical workflows.
arXiv AI
Jul 22
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
arXiv:2510. 12985v3 Announce Type: replace Abstract: We present SENTINEL, a framework for formally evaluating the physical safety of foundation model (FM)-based embodied agents.
arXiv AI
Jul 22
A Self-Supervised Framework for Space Object Behaviour Characterisation
arXiv:2504. 06176v4 Announce Type: replace-cross Abstract: Foundation Models, which leverage large neural networks pre-trained on unlabelled data before fine-tuning for specific tasks, are increasingly being applied to specialised domains.
arXiv AI
Jul 22
Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
arXiv:2505. 18934v2 Announce Type: replace-cross Abstract: Graph Anomaly Detection (GAD) in heterogeneous networks presents unique challenges due to node and edge heterogeneity.
arXiv AI
Jul 22
Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It
arXiv:2606. 12442v2 Announce Type: replace-cross Abstract: At present, loss of control risks have gained much prominence in public discussion, particularly in relation to AI, with extensive discourse present among academics, frontier labs, and even governments.
arXiv AI
Jul 22
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
arXiv AI
Jul 22
MIRAGE: Multi-scale Lesion-Informed Representation with Auxiliary Guidance for MRI Contrast Enhancement
arXiv:2607. 19137v1 Announce Type: cross Abstract: Inferring contrast enhancement from one pre-contrast breast MRI slice is underdetermined: post-contrast appearance contains physiological information that is not uniquely encoded in baseline anatomy.