Medical Subject Headings
PulseAugur coverage of Medical Subject Headings — every cluster mentioning Medical Subject Headings across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Recurrent Transformers gain traction amid OpenAI's Astra and Alibaba's research
The concept of Recurrent Transformers, where Transformer layers are repeatedly applied to the same sequence, has gained attention following reports that OpenAI's Astra model utilizes this technique. This approach aims t…
-
Model Context Protocol adds governed catalog API for AI data queries
The Model Context Protocol (MCP) is being extended with a governed catalog API to provide domain engineers with direct access to metadata about data assets. This new API aims to allow AI assistants to answer questions a…
-
Noesis architecture enhances Graph-RAG with adaptive parallelism and semantic discovery
Researchers have introduced Noesis, a novel Graph-RAG architecture designed to overcome limitations in current systems. Noesis employs four algorithms to address static chunking, adaptive scaling, and multi-domain deplo…
-
Noesis architecture enhances Graph-RAG with adaptive parallelism and cross-KB routing · 2 sources tracked
Researchers have introduced Noesis, a novel Graph-RAG architecture designed to overcome limitations in grounding large language models with domain-specific knowledge. Noesis employs four key algorithms: Bidirectional Gr…
-
Automattic's AI-powered CRM Mesh launches on Android
Automattic's personal CRM, Mesh, has launched on Android devices, enhancing its capabilities for users to manage their personal and professional networks. The app allows for detailed contact management, notes, and outre…
-
New MESH optimizer boosts MoE training efficiency, cuts memory use
Researchers have developed MESH, a novel optimization technique designed to improve the efficiency of training Mixture-of-Experts (MoE) models. Traditional memory-efficient optimizers like Sinkhorn struggle with MoE arc…
-
BioHiCL model enhances biomedical retrieval using hierarchical contrastive learning
Researchers have developed BioHiCL, a novel approach to biomedical information retrieval that utilizes hierarchical multi-label contrastive learning. This method leverages the structured supervision from Medical Subject…
-
Study: Evaluation design impacts MeSH feature performance gap
A new study published on arXiv investigates the impact of evaluation design on the performance gap between expert-assigned and automatically generated Medical Subject Headings (MeSH) when used as features in classificat…
-
Resource-efficient LLMs show promise for biomedical ontology generation
A new paper introduces MeSH-Rel-4K, a dataset of 4,000 semantic relationships from the Medical Subject Headings (MeSH) to evaluate resource-efficient Large Language Models (LLMs) in biomedical ontology generation. The s…
-
New research tackles large-scale retrieval challenges with unified frameworks
Two new research papers address challenges in large-scale retrieval systems, focusing on improving efficiency and accuracy. The first paper, MESH, proposes a unified framework for heterogeneous content retrieval that en…
-
China pioneers photonic computing for space-based AI, bypassing traditional chip limits
A Chinese company, Guangbenwei Technology, is pioneering photonic computing for space applications, aiming to overcome the limitations of traditional electronic chips in orbit. In collaboration with Dongfang Tianxuan, t…
-
LLMs show promise in generating research topic ontologies
Researchers explored how large language models can generate research topic ontologies across biomedicine, physics, and engineering. They introduced PEM-Rel-8K, a dataset of over 8,000 relationships from MeSH, PhySH, and…
-
New MCP server integrates 7 medical terminologies for LLMs
A new Model Context Protocol (MCP) server called medical-terminologies-mcp has been released, providing unified access to seven major medical terminology systems. This tool is designed to help Large Language Models (LLM…
-
KARITA model integrates knowledge for improved temporal adaptation in AI
Researchers have developed a new method called KARITA to address the challenges of temporal shifts in machine learning models. KARITA integrates rich knowledge sources, such as medical ontologies, to better adapt models…