Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.13840v1 Announce Type: new Abstract: A contract-logistics spare-parts operator is paid on order-level service: an order counts only if every requested line is fulfilled, yet forecasters ar...
arXiv:2609.13866v1 Announce Type: new Abstract: Group-relative policy optimization (GRPO and descendants) can discard no-contrast rollout groups through dynamic sampling, while practical implementati...
arXiv:2609.14180v1 Announce Type: new Abstract: Fault detection in autonomous VTOL aircraft is critical because even minor component degradations can rapidly destabilize multirotor vehicles operating...
arXiv:2609.14485v1 Announce Type: new Abstract: Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retri...
arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains p...
arXiv:2609.15643v1 Announce Type: new Abstract: Flow-matching diffusion models have recently emerged as a strong paradigm for high-fidelity visual generation. However, their prohibitively high fine-t...
arXiv:2609.15713v1 Announce Type: new Abstract: Recent approaches to 30-day hospital readmission prediction rely on pre-trained language models applied to discharge summaries. Although these methods...
arXiv:2609.15825v1 Announce Type: new Abstract: A self-supervised encoder is trained once, frozen, and reused through lightweight probes on tasks nobody named at training time; the practitioner's que...
arXiv:2609.13271v1 Announce Type: cross Abstract: Medical image segmentation needs diverse training data, but hospitals hold complementary scans they cannot share for privacy and regulatory reasons....
arXiv:2609.13348v1 Announce Type: cross Abstract: This paper presents ViFA-Council, a three-stage multi-agent framework that employs multiple large language models (LLMs) to tackle two culturally com...
arXiv:2609.13636v1 Announce Type: cross Abstract: Privacy-preserving inference via Torus Fully Homomorphic Encryption (TFHE) provides strong protection for sensitive data in outsourced deep learning...
arXiv:2609.13925v1 Announce Type: cross Abstract: This work studies the stability and convergence of augmented primal-dual dynamics when constraint values are estimated from samples. Unbiased constra...
arXiv:2609.15126v1 Announce Type: cross Abstract: Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more recently, conditional memory:...
arXiv:2609.14567v1 Announce Type: cross Abstract: Reinforcement learning (RL) has shown considerable promise for robotic decision-making, yet deploying multi-agent RL (MARL) on physical multi-robot s...
arXiv:2609.14815v1 Announce Type: cross Abstract: This paper introduces a novel framework for Regularized Multivariate Functional Principal Component Analysis (ReMFPCA) via Functional Singular Value...
arXiv:2609.14902v1 Announce Type: cross Abstract: Shapley value (SV)-based methods are the prevailing framework for feature attribution in machine learning, yet existing population-level Shapley esti...
arXiv:2609.14922v1 Announce Type: cross Abstract: For constant-stepsize stochastic approximation (SA), the iterates converge in distribution to a stationary law that depends on the stepsize $\alpha.$...
arXiv:2609.15847v1 Announce Type: cross Abstract: This paper proposes FREDI (Fair Resource Allocation for Edge Dual-Threshold Inference), a secure wireless edge-intelligence framework for event-trigg...
arXiv:2510.19266v3 Announce Type: replace Abstract: State-space models (SSMs) have emerged as promising alternatives to Transformers for sequence modeling. However, training competitive SSMs from scr...
arXiv:2606.13105v2 Announce Type: replace Abstract: We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is t...