Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 00301v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs) arise from heterogeneous failure mechanisms, making reliable detection difficult for any single global uncertainty score.
arXiv:2606. 00426v1 Announce Type: new Abstract: Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text.
arXiv:2606. 00400v1 Announce Type: new Abstract: Continual instruction tuning updates a language model through a sequence of new domains, yet each update can progressively erode previously learned capabilities and alignment behavior.
arXiv:2510. 03086v2 Announce Type: replace Abstract: For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly initialized FAQ remains a strong classical baseline, while existing GNN approaches struggle in the purely structural setting.
arXiv:2509. 22907v2 Announce Type: replace Abstract: Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learning models.
arXiv:2606. 02434v1 Announce Type: new Abstract: Precise parametric control over circuit geometry is essential for semiconductor inspection, yet obtaining sufficient real training data remains costly.
arXiv:2606. 00134v1 Announce Type: cross Abstract: Intrusion Detection Systems (IDS) in Internet of Things (IoT) environments face significant challenges due to data heterogeneity, lack of labeled data, and limited model interpretability.
arXiv:2606. 00462v1 Announce Type: cross Abstract: Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation.
arXiv:2606. 01783v1 Announce Type: cross Abstract: Digital platforms increasingly operate as isolated information silos, limiting their ability to construct comprehensive user representations across domains.
arXiv:2606. 01843v1 Announce Type: cross Abstract: Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that fail to transfer to unseen manipulations.
arXiv:2606. 02111v1 Announce Type: cross Abstract: As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse.
arXiv:2606. 02483v1 Announce Type: cross Abstract: Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external services before the agent commits to the branch.
arXiv:2606. 00045v1 Announce Type: new Abstract: Classical continuous-space neural networks fundamentally struggle to lock into exact mathematical symmetries, such as modular arithmetic and non-commutative algebra.
arXiv:2606. 00944v1 Announce Type: new Abstract: Applying differential privacy (DP) via DP-SGD to Low-Rank Adaptation (LoRA) is a natural approach for privacy-preserving fine-tuning.
arXiv:2603. 13312v2 Announce Type: replace-cross Abstract: Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences.
arXiv:2604. 26197v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential.
arXiv:2605. 25889v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from $95\%$ to under $5\%$.
arXiv:2606. 01028v1 Announce Type: new Abstract: Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals.
arXiv:2606. 02237v1 Announce Type: new Abstract: Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales.
arXiv:2606. 02339v1 Announce Type: new Abstract: Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood.