arXiv Machine Learning
Jun 8
Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring
arXiv:2606. 06871v1 Announce Type: new Abstract: Diagnosing 802.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 8
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
arXiv:2606. 07473v1 Announce Type: cross Abstract: Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input.
arXiv Machine Learning
Jun 8
Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making
arXiv:2606. 07088v1 Announce Type: new Abstract: Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness.
arXiv Machine Learning
Jun 8
Empirical Transfer Operators and Finite-Sample Change Detection for Noisy Expanding Interval Maps
arXiv:2606. 06785v1 Announce Type: cross Abstract: We study finite-sample change detection for one-dimensional noisy dynamical systems using partition-based empirical approximations of stationary behaviour.
arXiv AI
Jun 8
An Abstract Architecture for Explainable Autonomy in Hazardous Environments
arXiv:2606. 07211v1 Announce Type: cross Abstract: Autonomous robotic systems are being proposed for use in hazardous environments, often to reduce the risks to human workers.
arXiv AI
Jun 8
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
arXiv:2606. 06893v1 Announce Type: new Abstract: Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write.
arXiv Machine Learning
Jun 8
Self-Supervised Learning for Android Malware Detection on a Time-Stamped Dataset
arXiv:2604. 23025v2 Announce Type: replace-cross Abstract: Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actual release times, inflating accuracy and weakening real-world robustness.
arXiv Machine Learning
Jun 8
Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios
arXiv:2606. 06546v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for education requires measuring how models teach, not only what they know.
arXiv AI
Jun 8
PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
arXiv:2606. 07454v1 Announce Type: cross Abstract: Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates.
arXiv Machine Learning
Jun 8
Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions
arXiv:2606. 07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification.
arXiv AI
Jun 8
SV-Detect: AI-generated Text Detection with Steering Vectors
arXiv:2606. 07313v1 Announce Type: cross Abstract: Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks.
arXiv AI
Jun 8
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
arXiv:2606. 07451v1 Announce Type: cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space.
OpenAI Blog
Jun 8
Built to benefit everyone: our plan
A vision for the future of AI, focusing on access, safety, and shared prosperity as OpenAI works to ensure AGI benefits everyone.
Hugging Face Trending Papers
Jun 8
Synthetic but Not Realistic: The Evaluation Challenge in Generative Modelling for Structured Electronic Medical Records
Synthetic healthcare data are widely proposed as privacy-preserving substitutes for real patient data, yet their evaluation remains dominated by statistical similarity and predictive performance that do not reflect clinical validity. We introduce a multi-dimensional evaluation framework grounded in epidemiology, assessing descriptive fidelity, clinical utility, and structural validity, corresponding to descriptive, predictive, and causal questions.
arXiv AI
Jun 6
Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
arXiv:2601. 21700v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations.
arXiv AI
Jun 6
Evaluating the Utility of Personal Health Records in Personalized Health AI
arXiv:2605. 18937v2 Announce Type: replace Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex, potentially hindering insights.
arXiv AI
Jun 6
CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving
arXiv:2606. 06219v1 Announce Type: cross Abstract: End-to-end autonomous driving models often struggle to balance multi-modal maneuver generation with real-time inference constraints.
arXiv AI
Jun 6
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
arXiv AI
Jun 6
Towards World Models in Biomedical Research
arXiv:2606. 05925v1 Announce Type: new Abstract: A central goal of biomedicine is to understand, predict and ultimately control the dynamic mechanisms by which biological systems respond to perturbations, disease progression and therapeutic intervention.
arXiv AI
Jun 6
CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model
arXiv:2606. 06099v1 Announce Type: new Abstract: Whether Large Language Models (LLMs) exhibit covert psychological manipulation in complex human-AI interactions has garnered increasing safety concerns.