Restez à la pointe de la tech

Intelligence Artificielle

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models

arXiv:2608.17102v1 Announce Type: new Abstract: Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perception across speech, vision, and language, including emotion recognition. However, it remains unclear whether they recognize speech and facial emotion through shared affective functional units or modality-specific pathways. We…

Lire l'article

Intelligence Artificielle

A Glyph Is Not a Letter, a Token Is Not a Word, a Space Is Not a Space: What the Units of Voynichese Are Not

arXiv:2608.17096v1 Announce Type: new Abstract: The Voynich manuscript (Beinecke MS 408) is usually analysed on three unstated assumptions: that its glyphs are letters, that the strings between blanks are words, and that every blank is a word space. We test all three against the Zandbergen-Landini transliteration with matched prose, cipher, and pseudo-text controls and…

Lire l'article

Intelligence Artificielle

There is No Theoretical Curse of Multilinguality For Embedding Space Structure

arXiv:2608.17088v1 Announce Type: new Abstract: A central goal of multilingual NLP is to achieve high monolingual performance per language and cross-lingual alignment for large-scale language coverage with a multilingual model. The curse of multilinguality describes the phenomenon of degradation in multilingual model performance as we increase language coverage, posing a…

Lire l'article

Intelligence Artificielle

Uncertainty-Aware Decision Making in Multimodal Large Language Models

arXiv:2608.17084v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly answer questions whose correctness depends on visual, textual, temporal, acoustic, document, chart, or embodied evidence. Their failures are therefore not only linguistic. A fluent answer may conceal poor input quality, a perceptual error, weak grounding, conflict between…

Lire l'article

Intelligence Artificielle

Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecasting

arXiv:2608.17075v1 Announce Type: new Abstract: Next-encounter ICD forecasting predicts which standardized diagnosis codes will be documented at a future visit from the longitudinal record available beforehand. The task is prospective and multi-label: the target note does not yet exist, and several codes may be correct. Structured EHR foundation models capture recurrence and…

Lire l'article

Intelligence Artificielle

Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss

arXiv:2608.17051v1 Announce Type: new Abstract: Secondary use of electronic health records requires de-identification, yet existing systems miss \emph{institutionally situated} protected health information (PHI) such as hospital abbreviations, building names, and internal codes whose status is locally determined. We ask whether large language models (LLMs) with in-context…

Lire l'article