Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 00152v1 Announce Type: new Abstract: Predicting the magnitude of a CRISPRi perturbation's transcriptomic effect on held-out target genes is an important open problem in single-cell biology.
arXiv:2608. 02509v1 Announce Type: cross Abstract: Sequential decision-making in real-world applications often involves uncertainty about the environment's model.
arXiv:2605. 00762v2 Announce Type: replace Abstract: We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected set.
arXiv:2608. 02250v1 Announce Type: new Abstract: Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally updated models.
arXiv:2608. 00346v1 Announce Type: new Abstract: Data imbalance poses a major challenge in supervised classification, where the majority-class bias contributes to false negatives and overestimates classification accuracy.
arXiv:2608. 01423v1 Announce Type: cross Abstract: Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response.
arXiv:2608. 02271v1 Announce Type: new Abstract: Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners.
arXiv:2608. 01775v1 Announce Type: new Abstract: Compound flooding in managed coastal systems is influenced by hydrological conditions and water-management activity observed across multiple monitoring stations.
arXiv:2608. 01388v1 Announce Type: cross Abstract: Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequences in LLM agents.
arXiv:2608. 01473v1 Announce Type: cross Abstract: Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers.
arXiv:2511. 11686v4 Announce Type: replace Abstract: Speech enhancement (SE) requires high-fidelity reconstruction of clean speech that preserves linguistic and paralinguistic cues while maintaining high perceptual quality.
arXiv:2608. 00419v1 Announce Type: new Abstract: Large language models deployed in real-time, regulated settings face knowledge staleness, catastrophic forgetting, hallucination, and weak feedback loops.
arXiv:2604. 10933v2 Announce Type: replace-cross Abstract: Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications.
arXiv:2603. 18540v2 Announce Type: replace Abstract: The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge devices.
arXiv:2608. 01585v1 Announce Type: cross Abstract: Language model benchmarking is a difficult task.
arXiv:2607. 27594v2 Announce Type: replace Abstract: Post-training alignment in large reasoning models (LRMs) has significantly improved their adaptability to diverse safety compliance settings.
arXiv:2603. 28201v3 Announce Type: replace Abstract: We revisit the standard perturbation-based approach of Abernethy et al.
arXiv:2504. 21296v2 Announce Type: replace Abstract: Graph learning has evolved into Augmented Graph Learning (AGL) by integrating specialized machine learning (ML) techniques.
arXiv:2608. 02446v1 Announce Type: cross Abstract: Relevance evaluation plays a crucial role in personalized search systems, serving as a guardrail alongside user engagement metrics to ensure that search results align with user queries and intent.
arXiv:2506. 22423v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control.