arXiv Machine Learning
Jun 8
Sparsely gated tiny linear experts
arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv Machine Learning
Jun 8
Privacy Implies Stability: Information-Theoretic Generalization Bounds for Quantum Learning
arXiv:2602. 01177v3 Announce Type: replace-cross Abstract: We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms.
arXiv Machine Learning
Jun 8
Structure-Preserving Correction Learning for Sparse Bayesian Inference in Brain Source Imaging
arXiv:2606. 07196v1 Announce Type: new Abstract: Classical sparse Type-II Bayesian methods for M/EEG brain imaging support joint estimation of source and noise hyperparameters, but rely on fixed iterative update rules.
arXiv AI
Jun 8
SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.
arXiv AI
Jun 8
Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models
arXiv:2601. 22574v2 Announce Type: replace-cross Abstract: Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination.
arXiv AI
Jun 8
Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration
arXiv:2606. 07316v1 Announce Type: cross Abstract: Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-language proposals, the protocol must decide whether the round supports a commit, what kind of commit, or a typed safe abort.
arXiv AI
Jun 8
REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference
arXiv:2606. 07141v1 Announce Type: cross Abstract: Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owners may request the removal of their data from a trained model due to privacy or copyright concerns.
arXiv AI
Jun 8
From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability
arXiv:2606. 07150v1 Announce Type: cross Abstract: Agent-interoperability protocols such as A2A and MCP standardize what agents say to one another, but assume address-based transport over HTTP(S).
arXiv AI
Jun 8
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
arXiv:2512. 23128v2 Announce Type: replace-cross Abstract: Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking.
arXiv AI
Jun 8
SafeGene: Reusable Adapters for Transferable Safety Alignment
arXiv:2606. 06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful.
arXiv Machine Learning
Jun 8
Explaining Unsupervised Disease Staging in Huntington's Disease: Insights into Model Representations and Clusters
arXiv:2606. 07135v1 Announce Type: new Abstract: Huntington's disease (HD) is a progressive neurodegenerative disorder that affects motor, cognitive, and behavioral functions, where accurate characterization of disease progression remains essential to improve patient outcome and quality of life.
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.
arXiv AI
Jun 8
Automatic Causal Fairness Analysis with LLM-Generated Reporting
arXiv:2604. 27011v2 Announce Type: replace-cross Abstract: AutoML, intended as the process of automating the application of machine learning to real-world problems, is a key step for AI popularisation.
arXiv AI
Jun 8
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
arXiv:2510. 24561v3 Announce Type: replace-cross Abstract: LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention.
arXiv AI
Jun 8
Re-imagining ISO 26262 in the Age of Autonomous Vehicles: Enhancing Controllability through Transferability and Predictability
arXiv:2606. 07437v1 Announce Type: cross Abstract: The ISO 26262 standard defines functional safety for road vehicles through risk assessments based on Severity, Exposure, and Controllability, grounded in a human-driven vehicle paradigm.
arXiv Machine Learning
Jun 8
GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution
arXiv:2606. 06892v1 Announce Type: new Abstract: Scalable data attribution methods typically assign isolated utility scores to individual training examples.
arXiv AI
Jun 8
MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion
arXiv:2509. 17446v3 Announce Type: replace-cross Abstract: Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions.
arXiv Machine Learning
Jun 8
Unmixing ATR-{\mu}FTIR spectroscopic images of cross-sections of historical oil paintings
arXiv:2603. 06673v2 Announce Type: replace-cross Abstract: Spectroscopic imaging (SI) has become central to heritage science because it enables non-invasive, spatially resolved characterisation of materials in artefacts.
arXiv Machine Learning
Jun 8
Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication
arXiv:2509. 11208v3 Announce Type: replace-cross Abstract: Transformers used for evidence-grounded binary adjudication (e.
arXiv Machine Learning
Jun 8
A Rolling-Window Framework for Churn Prediction and Behavioral Driver Identification
arXiv:2606. 06776v1 Announce Type: new Abstract: Customer churn prediction is a central task in customer analytics, particularly in non-contractual, pay-per-use service environments where disengagement is not explicitly observed and must be inferred from behavioral inactivity.