Category
8,786 papers
A bilingual evaluation suite of 231 Vietnamese--English question--answer pairs from Vietnamese labour law is introduced, and six automatic diagnostics for faithfulness to retrieved evidence are introduced, covering citations, modality, exceptions, procedures, conclusions, and evidential support.
Planned Test-Time Scaling (PTTS) provides a general framework for improving test-time scaling by coordinating reasoning branches, with zero-shot and trainable instantiations that yield substantial performance gains.
It is argued that the appropriateness of a response offset, whether delayed silence or anticipatory overlap, is conditional on the speaker's latent intent, identifiable only from that speaker's behavior.
Vietnam's Personal Data Protection Law (Law No. 91/2025/QH15) and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establish and maintain Records of Processing Activities (RoPA). Manual RoPA preparation is labor-intensive, while cloud-hosted large language models (LLMs) may conflict with d...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely reproduces the same score, making controlled studies of training phenomena impractical. We present WebMRE, an offline benchmark of 541 tasks and 5,293 steps derived from succ...
Ruby-ASR is presented, which refines the conventional target into a span-bound orthographic--lexical-reading sequence and shows that refining the recognition target can improve lexical-reading recovery without sacrificing readable orthographic transcription.
This work studies whether task-specialist models should be handled by separate task-specialist models or by a single model trained through multi-task training, sequential updates, or model merging, and concludes with practical guidelines for selecting fine-tuning strategies in real-world settings.
ChinaUnicom DataAgent (UniDataAgent) is presented, an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution and has the potential to be replicated in other enterprises.
A method for distilling sequential computation by replacing spans of input tokens with collapsed representations, computed on the fly by a lightweight merge module, allowing pretrained models to operate on compressed inputs without architectural changes or re-training.
Probabilistic question-answering systems -- whether large language models (LLMs) themselves, retrieval-augmented generation (RAG), or trained multi-hop retrievers -- conflate"what is known"and"how to reason"into a single probabilistic computation: hallucination cannot be eradicated, evidence chains cannot be audited, a...
Hidden diffusion trajectories are established as actionable signals for selective test-time reasoning repair and LOCKR, a hidden-state trajectory-guided planner that decides when to allocate additional computation, expands a structured set of targeted repair branches, and selects the most promising continuation using t...
Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface form. We introduce UGTPhon, the first grapheme-to-phoneme (G2P) benchmark for UGT in English, Vietnamese, and Korean, together with an inference-grounded...
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
