Category
3,366 papers
Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap as the problem of agentic abstention, and existing approaches typically optimize...
Adapting general-purpose large language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is especially challenging because model updates change the error distribution, requiring strategies to be continually refined. We introduce ImproveAnyTask,...
LLM agents are starting to own the full customer experience. Soon, LLMs may be selling and buying on behalf of companies and customers respectively. Small models are more cost-efficient at scale, but can reinforcement learning train them into competent sellers? We train four Gemma 4 checkpoints (2.3B to 31B effective p...
We develop and test a theory of language model representations in which there exist atomic features. Our main theoretical insight is that in such a model, sparse dictionaries (e.g., SAEs) of increasing size recover an increasing prefix of the most prevalent atoms in the training data. This"recovery principle"yields thr...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Small language models (SLMs) offer a promising foundation for on-device agents through low-latency, resource-efficient inference, yet limited reasoning and planning capabilities constrain their performance on long-horizon tasks requiring multi-step interaction with the environment. Step-level collaboration between SLMs...
Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch together with multiple draft branches in a single forward pass. While prior DLLM acceleration methods primarily exploit temporal redundancy a...
Large language models (LLMs) can generate clinical narratives that are insufficiently grounded in patient-specific evidence. In traditional Chinese medicine (TCM), errors can propagate from etiology and pathogenesis through syndrome diagnosis and treatment principles to prescription generation. We developed TCMClinical...
An annotation framework covering key aspects of travel history, including destination, exposures, travel duration, and multiple temporal variables is developed, used to annotate a corpus of 100 clinical case reports by five clinicians, yielding over 5,000 clinician annotations.
Whether an open-weight pipeline running entirely on one consumer graphics card can accurately extract clinical information from faxed referral packets is evaluated.
Findings suggest model scaledoes not fully determine performance within a fixed pipeline,supporting compact local models as a practical, low-cost, lowlatencyalternative for enterprise deployment.
Semantic scheduling is formulates as an uncertainty-aware framework that builds an admissible, quality-controlled scheduling instance from incomplete artifacts and optimizes it into feasible calendar-resource schedules.
Yemeni students in Saudi universities occupy an unusual position. They study abroad, yet in a country that shares their language, religion, and much of their culture, while their families remain in a state that has been at war since 2014. Depression and anxiety are common among international students generally, and rec...
A Blog post by Liquid AI on Hugging Face
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.
