Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.14170v1 Announce Type: cross Abstract: Distributed multiple testing asks $N$ sites to control a global false discovery rate (FDR) under a tight communication budget. The greedy interval-ag...
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understandin...
arXiv:2609.13731v1 Announce Type: new Abstract: The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling rec...
arXiv:2609.14512v1 Announce Type: new Abstract: Virtual worlds now host classrooms, meetings, conferences, shops, and social venues, and nearly every interaction they expose assumes a user who can sc...
arXiv:2609.15134v1 Announce Type: new Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through r...
arXiv:2609.15207v1 Announce Type: new Abstract: Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before ele...
The paper investigates unsupervised term discovery in speech, comparing centre-based clustering methods like K‑means with graph‑based clustering using the Leiden algorithm. It finds that graph clustering produces lexicons whose type frequencies follow a Zipfian distribution, outperforming K‑means, GMM, and BIRCH across word‑ and syllable‑level discovery in three languages. Agglomerative clustering with average linkage also performs well but is less efficient and offers less control over the distribution.
arXiv:2609.14615v1 Announce Type: cross Abstract: Unified motion generation and understanding is crucial for embodied AI systems that can both synthesize and interpret human actions in open-world env...
arXiv:2609.14861v1 Announce Type: cross Abstract: A deployed language model may refuse a harmful request in English yet comply with its faithful translation, revealing a cross-lingual safety failure...
arXiv:2609.15603v1 Announce Type: cross Abstract: Accurate PSMA PET/CT interpretation is central to prostate cancer management, yet existing PET/CT AI models typically address isolated tasks. We prop...
arXiv:2602.20723v3 Announce Type: replace Abstract: Multimodal recommenders combine collaborative behavior with visual and textual item evidence, whose usefulness varies across user-item interactions...
arXiv:2603.02504v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently gener...
arXiv:2505.08123v2 Announce Type: replace-cross Abstract: Multi-material decomposition (MMD) enables quantitative reconstruction of tissue compositions in the human body, supporting a wide range of c...
arXiv:2506.17871v4 Announce Type: replace-cross Abstract: Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this cons...
arXiv:2603.07551v3 Announce Type: replace-cross Abstract: Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Genera...
arXiv:2603.19574v2 Announce Type: replace-cross Abstract: Conversational AI systems are increasingly used for personal reflection and emotional disclosure, raising concerns about their effects on vul...
arXiv:2609.13518v1 Announce Type: new Abstract: We present GeoTTER, a novel framework that redefines optimal transport in the realm of zero-shot classification. Conventional methods often suffer from...
arXiv:2609.14174v1 Announce Type: new Abstract: Asked to describe what one of six speakers in a recording talks about, audio language models describe the right one on 6 to 16% of trials, below the 16...
arXiv:2609.15128v1 Announce Type: new Abstract: Streaming omni-modal models must decide what and when to answer from the video chunks and synchronized audio observed so far. Visual cues often support...
arXiv:2609.07061v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is...