Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 11600v1 Announce Type: new Abstract: We propose a collaborative meta-learning framework for distributed Bayesian optimization matching centralized performance without raw-data exchange.
arXiv:2607. 10476v1 Announce Type: cross Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions.
arXiv:2607. 10233v1 Announce Type: cross Abstract: Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments.
arXiv:2607. 09753v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success across diverse domains, with performance closely related to the denoising backbones that parameterize the score function.
arXiv:2607. 10526v1 Announce Type: new Abstract: Stateful personal agents increasingly maintain long-term user profiles, episodic memories, and reusable skills.
arXiv:2607. 09973v1 Announce Type: cross Abstract: Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable variation, and remain efficient for practical workflows.
arXiv:2607. 10112v1 Announce Type: cross Abstract: Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settings.
arXiv:2607. 10539v1 Announce Type: new Abstract: Existing approaches to infer user traits and generate responses consistent with a persona rely on static prompting.
arXiv:2607. 10555v1 Announce Type: cross Abstract: Generative Large Language Models (LLMs) have revolutionized information retrieval, yet their strictly parametric nature frequently leads to severe factual hallucinations when confronted with complex queries beyond their epistemic boundaries.
arXiv:2607. 11334v1 Announce Type: new Abstract: Large language models can produce superficially legal twelve-tone scores that collapse into degenerate textures.
arXiv:2607. 11364v1 Announce Type: cross Abstract: Generating immersive, synchronized and cinematic audio for long-form textual narratives remains a significant challenge in multi-modal AI.
arXiv:2511. 17688v2 Announce Type: replace-cross Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs.
arXiv:2607. 10014v1 Announce Type: cross Abstract: Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS).
arXiv:2607. 09772v1 Announce Type: cross Abstract: Autonomous driving systems require reliable safety validation before real-world deployment.
arXiv:2506. 22036v2 Announce Type: replace Abstract: With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees.
arXiv:2607. 11346v1 Announce Type: new Abstract: Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs).
arXiv:2607. 11269v1 Announce Type: new Abstract: Decision support systems (DSS) increasingly run retention what-if analysis on synthetic customer populations, because privacy constraints preclude unrestricted use of real data.
arXiv:2607. 10212v1 Announce Type: new Abstract: Knowledge Graphs (KGs) are increasingly constructed through automated extraction pipelines; however, such systems often introduce spurious or incomplete triples, which degrade downstream performance.
arXiv:2607. 10930v1 Announce Type: cross Abstract: Generative models often represent signals as dense grids of amplitudes, blurring sharp transients that are crucial for the correctness of physical signals.
arXiv:2607. 11560v1 Announce Type: cross Abstract: Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning.