Category
9,261 papers
Evidence on GenAI-MI chatbots across system design, safety, MI quality, user perceptions, and intervention outcomes is characterized, with positive findings more consistent for short-term motivation than sustained behavioral or functional change.
This work proposes MME-Safety, a rigorously verified benchmark featuring a unique four-dimensional annotation schema that categorizes risk scenarios, harm severity, and modality-specific stealth levels and introduces a hierarchical evaluation framework to assess fundamental response reliability, actual risk exposure, a...
SPARE (Semantic Prediction for Audio REasoning), which introduces a register token aligned with the final conclusion using a cosine similarity loss with a Sentence-BERT embedding, conditions the model's latent space with the target semantic goal before reasoning begins.
Anxiety is among the most common mental health conditions, and people often write about it online well before seeking clinical help. Practitioners building detection tools face a concrete choice: call a frontier commercial model, fine-tune a smaller model in-house, or deploy a conventional classifier. We compare six co...
Reach audiences
Advertise in front of researchers, engineers, and readers.
The method repurposes DR-RL trajectories, which naturally contain search histories, visited webpages, evidence snippets, and final-answer supervision, and replaces the compact snippets and webpage summaries in each trajectory with the full contents of their corresponding URLs, producing substantially longer multi-docum...
COAL-SQL is proposed, a unified framework combining Coverage-Guided Augmentation (CGA) and Failure-Driven Learning (FDL) that achieves 64.9% execution accuracy on the BIRD development set and outperforms baselines trained at comparable scale.
PECT consistently improves reconstruction performance across multiple phoneme-based visual speech recognition frontends, including visual automatic speech recognition (V-ASR), point visual automatic speech recognition (PV-ASR), and head-pose-aware visual speech recognition (HP-VSR) variants.
This study provides a systematic assessment of LLMs detection capability of LLMs generated fake news across typical generation scenarios and demonstrates that the generation strategy strongly influences detectability.
Background: The Voynich Manuscript is a fifteenth-century codex written in an unknown script whose content remains undeciphered. Previous studies suggest that its statistical properties resemble those of natural languages, while its illustrations - primarily plants - recall medieval herbals. Methods: We present a multi...
A comprehensive taxonomy of common misconfiguration types is introduced, offering a structured framework to better understand and categorize these issues and provides novel insights into enhancing misconfiguration detection methodologies.
This paper presents the Transsion Speech Team submission to Task 1 of the MLC-SLM 2026 Challenge, which focuses on speaker-attributed transcription for multilingual conversational speech. We propose a cascaded framework consisting of three components: a speaker diarization module, a long-form multilingual ASR module, a...
We introduce TatBLiMP, the first benchmark of linguistic minimal pairs for Tatar (tt, ISO 639-3 tat), a Qypchaq Turkic language written in Cyrillic. To our knowledge it is the first grammaticality evaluation for Tatar language models of any kind, since even the 101-language MultiBLiMP does not include Tatar. TatBLiMP c...
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
