Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605. 16713v2 Announce Type: replace-cross Abstract: Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between.
arXiv:2606. 13341v1 Announce Type: cross Abstract: We present a Dual-Domain Equivariant Generative Adversarial Network (DDE-GAN) for multimodal CT-PET image synthesis.
arXiv:2605. 26144v2 Announce Type: replace-cross Abstract: We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents.
arXiv:2304. 13836v5 Announce Type: replace-cross Abstract: The RemOve-And-Retrain (ROAR) benchmark is widely used to evaluate feature attribution methods, yet its validity remains underexplored from an information-theoretic perspective.
arXiv:2606. 13211v1 Announce Type: new Abstract: AI systems are being deployed across medical imaging faster than their failure modes are understood.
arXiv:2606. 13436v1 Announce Type: new Abstract: Evaluation in machine learning is typically treated as a neutral measurement process.
arXiv:2606. 12415v1 Announce Type: cross Abstract: The rapid global expansion of artificial intelligence regulation has generated, across multiple jurisdictions, a demand for legal expertise dedicated to AI that the market has addressed in a fragmented manner.
arXiv:2606. 13007v1 Announce Type: cross Abstract: Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying cell populations and resolving tissue heterogeneity.
arXiv:2512. 15134v2 Announce Type: replace-cross Abstract: A goal of interpretability is to recover disentangled representations of latent concepts (features) from the activations of neural networks.
arXiv:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.
arXiv:2507. 05019v2 Announce Type: replace-cross Abstract: In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates.
arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.
arXiv:2605. 27628v2 Announce Type: replace Abstract: As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge.
arXiv:2606. 12418v1 Announce Type: cross Abstract: The rapid proliferation of large language models (LLMs) has produced a striking cultural practice: using conversational AI for divination.
arXiv:2606. 12424v1 Announce Type: cross Abstract: As generative AI and low-code workflow platforms become routine in software practice, a key educational question is whether the next generation of computer engineers will accept these tools as useful, usable, and worthy of sustained engagement.
arXiv:2606. 12429v1 Announce Type: cross Abstract: Muse Spark is the latest large language model developed by Meta.
arXiv:2606. 13621v1 Announce Type: new Abstract: Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions.
arXiv:2606. 12988v1 Announce Type: cross Abstract: This paper introduces a new methodology for real-time prediction of ergonomic and non-ergonomic human poses using volumetric video data in three dimensions.
arXiv:2606. 13311v1 Announce Type: cross Abstract: Contextual anomaly detection aims to identify abnormal behavior conditional on context variables, but practical deployments often face highly imbalanced context distributions where rare regimes can be critical information.
arXiv:2606. 13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented.