Category
3,366 papers
This repository contains an Agda implementation of the dependent SECD machine and the Dependent Abstract Machine (DAM), with a formalization of their type safety and dependent SECD machine's termination. Getting started (Kick the tires) To start, install Agda version 2.8.0 (instructions). Download and unzip the artifac...
A small, fast text classifier can answer the easy cases itself and pass only the uncertain ones to a large language model. Version 1.0 of this work estimated how much time such a two-stage setup saves; this version measures it while both models run on one consumer graphics card. The two-stage setup made the average dec...
Batch active learning for ligand discovery requires a recurring decision about whether to exploit high predicted affinity, reduce model uncertainty, or broaden chemical coverage. We test whether a language model can make this strategy-level decision while candidate ranking and label revelation remain controlled by a de...
Small language models could support several product-understanding operations within a retailer’s infrastructure, but evidence of task accuracy is easily con-founded with evidence of generalization or serving efficiency. We study QLoRA adaptation of Qwen3-1.7B for query–product relevance, listing identity, functional re...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Background: The impostor phenomenon (IP), the internal experience of intellectual phoniness despite objective competence, is poorly understood in Arabic-speaking populations, particularly its interplay with coping and attainment. This study estimated IP prevalence, characterized coping, and modeled cumulative grade poi...
Large language models for code have achieved strong performance across diverse software analytics tasks, yet their real-world adoption remains limited by high computational demands, slow inference speeds, significant energy consumption, and environmental impact. Knowledge distillation (KD) offers a practical solution b...
Background/Objectives: Specialist hepatology capacity is small relative to the population needing assessment, so most decisions about whom to investigate for chronic liver disease fall to non-specialists guided by static laboratory indices reported in isolation. This study presents HepDecide, a standards-oriented decis...
Preprint notice: This is the submitted pre-review author version of a manuscript submitted to BMJ Innovations on 22 September 2026. This version predates peer review and has not been revised in response to reviewer comments. The record includes the main manuscript and supplementary material. Abstract Background: Health...
Executive Summary Serbia’s artificial intelligence (AI) landscape is evolving rapidly. It is being shaped by parallel advances in digitalisation, innovation, industrial adoption and emerging regulatory frameworks. In recent years, the country has invested in modernising public services, strengthening its research and i...
Large Language Models (LLMs) offer transformative potential for enterprise automation, particularly within the highly complex and data-dense environments of transportation, supply chain management, and intralogistics. However, deploying foundational models in these specialized domains frequently results in a critical f...
Version 1.4 — Falsifiable test (5 languages). A stand-alone paper continuing V1.2 (Section 9) and V1.3 (Section 10). In V1.2 the boundaries of the UNU interval are α = ε and Ω = 2 − ε, with ε a hyperreal infinitesimal. This note tests what happens if ε is instead a positive real number. Two physically distinct readings...
Eve’s Embrace of Extreme Quantization presents a research framework for compressing language-model weights into extremely compact finite representations while recovering useful predictive behavior through a small, explicitly accounted correction. Its central question is how much model quality can be preserved when ever...
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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 use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
