Latest AI/ML News
8160 articles · arXiv cs.AI
arXiv:2610.05712v1 Announce Type: cross Abstract: We introduce a framework for multi-bit text watermarking with security defined directly through $f$-…
arXiv:2610.05709v1 Announce Type: cross Abstract: Language-model agents are evolving into long-running services that interact with models, tools, comp…
arXiv:2610.05684v1 Announce Type: cross Abstract: Modern deep generative models are primarily studied for their ability to generate realistic samples,…
arXiv:2610.05682v1 Announce Type: cross Abstract: Knowing domain rules does not guarantee applying them to a case. We study this distinction in tradit…
arXiv:2610.05647v1 Announce Type: cross Abstract: The Lindblad master equation is the standard framework for describing the non-unitary evolution of o…
arXiv:2610.05622v1 Announce Type: cross Abstract: Tool-using AI agents are increasingly deployed across enterprise software systems, yet widely used b…
arXiv:2610.05610v1 Announce Type: cross Abstract: Embodied, ego-centric intelligence fundamentally requires the ability to comprehend spatial audio wi…
arXiv:2610.05608v1 Announce Type: cross Abstract: We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-aud…
arXiv:2610.05601v1 Announce Type: cross Abstract: Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance…
arXiv:2610.05600v1 Announce Type: cross Abstract: High-dimensional bioinformatics data, characterized by a large number of features relative to the nu…
arXiv:2610.05598v1 Announce Type: cross Abstract: An organization often holds too little labeled data to train a model that generalizes, and the recor…
arXiv:2610.05586v1 Announce Type: cross Abstract: As Large Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and…
arXiv:2610.05584v1 Announce Type: cross Abstract: Extra inference compute is usually spent on sampling more reasoning chains. We study where inside an…
arXiv:2610.05577v1 Announce Type: cross Abstract: A linear probe can show that a label is recoverable from a model's hidden states, but not whether th…
arXiv:2610.05575v1 Announce Type: cross Abstract: Much of expressive text-to-speech research rests on an untested assumption that written text carries…
arXiv:2610.05571v1 Announce Type: cross Abstract: In safety-critical domains such as autonomous driving, systems must be evaluated across a large numb…
arXiv:2610.05563v1 Announce Type: cross Abstract: Small language model (SLM) agents need safety controls that track consequences across tool calls wit…
arXiv:2610.05559v1 Announce Type: cross Abstract: Industrial sequential recommender systems operate over massive item catalogs (e.g., 10^5--10^7 items…
arXiv:2610.05544v1 Announce Type: cross Abstract: Real-world deployment of active learning typically forces practitioners to choose an acquisition str…
arXiv:2610.05541v1 Announce Type: cross Abstract: Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs.…