arXiv:2602.12370v1 Announce Type: new Abstract: Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilities due to the limited scale of available text-motion pairs. Furthermore, prior methods typically convert motion into discrete representations via quantization to integrate […]

Ver mais

arXiv:2603.05520v1 Announce Type: new Abstract: Sequential multi-agent large language model (LLM) systems are increasingly deployed in sensitive domains such as healthcare, finance, and enterprise decision-making, where multiple specialized agents collaboratively process a single user request. Although individual agents may satisfy local privacy constraints, sensitive information can still be inferred through sequential composition and intermediate representations. In this work, we study emph{compositional privacy leakage} in sequential LLM agent pipelines. We formalize leakage using mutual information and derive a theoretical […]

Ver mais

arXiv:2601.04222v1 Announce Type: new Abstract: Many documentaries on early house and techno music exist. Here, protagonists from the scenes describe key elements and events that affected the evolution of the music. In the research community, there is consensus that such descriptions have to be examined critically. Yet, there have not been attempts to validate such statements on the basis of audio analyses. In this study, over 9,000 early house and techno tracks from Germany and the United States […]

Ver mais

arXiv:2603.02231v1 Announce Type: new Abstract: Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based numerical methods like Finite Element Method (FEM) provide high accuracy but struggle with large-scale or high-frequency problems due to prohibitive computational costs. Pure data-driven approaches excel in speed but often lack sufficient labeled data for complex scenarios. Physics-informed neural networks (PINNs) integrate physical principles into machine learning models, offering a promising solution by bridging these gaps. […]

Ver mais

arXiv:2601.22246v1 Announce Type: new Abstract: As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution has become increasingly important. Watermarking is a promising approach, but existing methods either provide only binary signals or distort the sampling distribution, degrading text quality; distortion-free approaches, in turn, often suffer from weak detectability or robustness. We propose MirrorMark, a multi-bit and distortion-free watermark for LLMs. By mirroring sampling randomness in a measure-preserving manner, […]

Ver mais

arXiv:2602.00997v1 Announce Type: new Abstract: Automatic Prompt Optimization (APO) is a powerful approach for extracting performance from large language models without modifying their weights. Many existing methods rely on trial-and-error, testing different prompts or in-context examples until a good configuration emerges, often consuming substantial compute. Recently, natural language feedback derived from execution logs has shown promise as a way to identify how prompts can be improved. However, most prior approaches operate in a bottom-up manner, iteratively adjusting the […]

Ver mais

Developments in the machine learning voting domain have shown both promising results and risks. Trained models perform well on ballot classification tasks (> 99% accuracy) but are at risk from adversarial example attacks that cause misclassifications. In this paper, we analyze an attacker who seeks to deploy adversarial examples against machine learning ballot classifiers to compromise a U.S. election. We first derive a probabilistic framework for determining the number of adversarial example ballots that must be printed to […]

Ver mais

arXiv:2603.08887v1 Announce Type: new Abstract: Building on existing $hp$-adaptive algorithms driven by equilibrated-flux estimators from [ESAIM Math. Model. Numer. Anal. 57 (2023), 329–366] and the references therein, we propose a novel $h$-adaptive algorithm for a fixed polynomial degree $p$. We consider a conforming finite element discretization of the Poisson equation in two or three space dimensions. Supposing piecewise polynomial right-hand side, we show that the algorithm yields error contraction at each step, with a contraction factor that is […]

Ver mais