Category
3,200 papers
Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offers a promising path: privileged information extracted from experience is provided to a teacher, whose behavior is then distilled into a student model that has no access...
Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document content, and reason over the collected evidence. Even advanced vision-language models (VLMs) can overlook sparse evidence and struggle with cross-modal reasoning in a single...
A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compresses its library, even when the skill is wrong. That is fine until the answers have to be exactly right: over a table of transactions, a total is either right or wrong....
Objective Autonomous vehicle (AV) crashes continue to occur, indicating the need for a comprehensive understanding of their characteristics to support safety management in future mixed-traffic environments. Previous studies employing text mining or rule extraction have faced limitations in generalizing findings due to...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Low-altitude unmanned aerial vehicles (UAVs) require compact multimodal inference for perception, environment understanding, and planning-oriented reasoning. Vision-language models (VLMs) provide a shared interface for these tasks, but long visual-token sequences increase language-model prefill computation, sequence-de...
Background Structured exercise may benefit executive function across childhood, adolescence, and later life, but whether effects vary by executive-function domain, developmental stage, or qualitative exercise characteristics remains uncertain. Methods We conducted a systematic review and three-level meta-analysis of ra...
Users often need answers from lengthy documents without knowing the exact terms used in the source. DocuMind AI is a document question-answering prototype that combines semantic retrieval with large language model generation. It accepts PDF, DOCX, TXT, and Markdown files, extracts and splits their text, creates embeddi...
Panoramic dental radiographs are routinely used for diagnosis and treatment planning, yet their interpretation remains time-consuming and highly dependent on clinical expertise. Although Vision–Language Models (VLMs) have shown promising capabilities for medical report generation, their application to dental radiology...
Some sign language avatars work like a phrase book. They play a recorded sign for each word in their dictionary and fingerspell the other meaningful words, such as nouns, verbs and names, spelling them letter by letter with the hand alphabet, which takes longer than signing. This paper measures how much an Internationa...
This article examines the teaching of culture-bound phraseological units in F. Scott Fitzgerald’s The Great Gatsby from a linguocultural and pedagogical perspective. The principal purpose is to develop and justify a didactic model designed to strengthen students’ translation competence and intercultural competence in h...
Background Yangxin Dingji Capsule (YXDJ), a modern Chinese patent medicine derived from the classic Zhigancao Decoction, is commonly used as an adjuvant therapy for atrial fibrillation (AF). This study aimed to comprehensively evaluate the efficacy and safety of YXDJ as an adjuvant therapy in AF patients. Materials and...
Email spam detection in English has been studied extensively under full supervision, but for low-resource languages such as Turkish the largest public dataset is more than an order of magnitude smaller, and every existing Turkish spam detector assumes full supervision. This study asks whether spam can be detected from...
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.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring 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.
