HighlightCurated by Aramai Editorial

Efficient Estimation of Word Representations in Vector Space

Proposes two new architectures for learning continuous word vector representations efficiently from very large datasets.

The paper proposes two novel architectures for computing continuous vector representations of words from very large datasets. Representation quality is measured on a word similarity task and compared against prior neural-network-based techniques. The authors report large accuracy gains at much lower computational cost, learning high-quality word vectors from a 1.6 billion word dataset in under a day. These vectors also achieve state-of-the-art results on a test set measuring syntactic and semantic word similarities.

Based on: Efficient Estimation of Word Representations in Vector Space · International Conference on Learning Representations

HighlightCurated by Aramai Editorial

GloVe: Global Vectors for Word Representation

Introduces GloVe, a global log-bilinear regression model unifying matrix factorization and context-window methods for word vectors.

Prior word-vector methods captured semantic and syntactic regularities through vector arithmetic, but why these regularities arose was unclear. The authors make explicit the properties needed for such structure to emerge and propose GloVe, a global log-bilinear regression model combining matrix factorization with local context-window approaches. It trains only on nonzero entries of a word-word co-occurrence matrix. The resulting vectors score 75% on a word analogy task and outperform related models on similarity and named entity recognition.

Based on: GloVe: Global Vectors for Word Representation · Conference on Empirical Methods in Natural Language Processing

HighlightCurated by Aramai Editorial

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Devlin et al. present BERT, a bidirectional Transformer pretraining method that set new state-of-the-art results on eleven NLP tasks.

BERT pre-trains deep bidirectional representations by jointly conditioning on left and right context in every layer, unlike prior left-to-right language models. A single pretrained BERT model can be fine-tuned with one extra output layer for many tasks, pushing GLUE to 80.5, MultiNLI accuracy to 86.7%, and SQuAD v1.1 F1 to 93.2 — new state-of-the-art results across eleven NLP benchmarks.

Based on: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding · North American Chapter of the Association for Computational Linguistics

HighlightCurated by Aramai Editorial

Attention is All you Need

Vaswani et al. propose the Transformer, an architecture built solely on attention, replacing recurrence and convolution.

The Transformer dispenses with recurrent and convolutional layers entirely, relying only on attention mechanisms. It is more parallelizable and faster to train than prior encoder-decoder models, reaching 28.4 BLEU on WMT 2014 English-to-German and a new state-of-the-art 41.8 BLEU on English-to-French after 3.5 days of training on eight GPUs.

Based on: Attention is All you Need · Neural Information Processing Systems

HighlightCurated by Aramai Editorial

Deep Residual Learning for Image Recognition

He et al. introduce residual learning, letting networks hundreds of layers deep train reliably and win ILSVRC/COCO 2015.

Very deep networks are hard to optimize directly. The authors reformulate layers to learn residual functions relative to their inputs, which makes substantially deeper networks (up to 152 layers) easier to train and more accurate. Residual nets took 1st place in ILSVRC 2015 classification (3.57% error) and drove a 28% relative improvement on COCO object detection.

Based on: Deep Residual Learning for Image Recognition · Computer Vision and Pattern Recognition

HighlightCurated by Aramai Editorial

Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents

A survey on persistent memory, state, and governance in LLMAgents.

The paper surveys the literature on always-on agents, which are systems whose future behavior depends on durable state accumulated across earlier interactions. It introduces a framework for evaluating these systems and connects them to databases, distributed systems, formal methods, capability security, and machine unlearning. The survey focuses on six diagnostic axes: authority, scope, mutability, provenance, recoverability, and actionability.

Based on: Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents · arxiv.org

HighlightCurated by Aramai Editorial

Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!

Paper on improving question answering systems with large language models using ontologies.

This paper presents an approach to improve the accuracy of question answering systems with large language models by leveraging ontologies. The authors propose a method that consists of ontology-based query check and LLM repair, which increases the overall accuracy to 72%. The results provide further evidence that investing knowledge graphs, namely the ontology, provides higher accuracy for LLM-powered question-answering systems.

Based on: Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue! · arxiv.org

HighlightCurated by Aramai Editorial

Google zero-click searches hit 68% in early 2026: Study

A study reports that Google zero-click searches reached 68% in early 2026.

The study highlights the increasing trend of users relying on AI-powered search results, reducing click-through rates and potentially impacting organic traffic. The article discusses the implications for SEO strategies and suggests ways to adapt to this shift. It also mentions related topics such as AI Overviews, featured snippets, and content repurposing.

Based on: Google zero-click searches hit 68% in early 2026: Study · searchengineland.com

HighlightCurated by Aramai Editorial

oxigraph

A Rust-based graph database implementing the SPARQL standard.

Oxigraph is a graph database written in Rust that implements the SPARQL standard. It provides a compliant, safe, and fast graph database based on the RocksDB key-value store. Oxigraph also includes utility functions for reading, writing, and processing RDF files.

Based on: oxigraph · git.nextgraph.org

HighlightCurated by Aramai Editorial

SHACL 1.2 Rules

This document defines SHACL Rules, a language for describing the structure of RDF graphs.

SHACL 1.2 Rules is a specification that defines a language for describing the structure of RDF graphs and provides inferencing with the generation of new RDF data from a combination of rules and a base data graph. The document defines the syntax and semantics of rule-based inference, including basic patterns, recursion, filtering, negation, assignment, and importing rules. It also covers the evaluation of a rule set and the relationship between SHACL Rules and SPARQL.

Based on: SHACL 1.2 Rules · w3.org

HighlightCurated by Aramai Editorial

Anatomy, Head and Neck, Mandible

A medical resource describing the anatomy and structure of the human mandible.

The mandible is the largest bone in the human skull, forming the lower jawline. It articulates with the skull base at the temporomandibular joints, allowing a range of movements. The mandible is also the insertion point for muscles involved in facial expression and has a complex structure and function.

Based on: Anatomy, Head and Neck, Mandible - StatPearls - NCBI Bookshelf · ncbi.nlm.nih.gov

HighlightCurated by Aramai Editorial

Vault-LD: an open spec for Markdown vaults as linked data

An open format for knowledge that enables two-way conversion between Markdown notes and RDF graphs.

Vault-LD is a specification for converting Markdown notes into RDF graphs, enabling the sharing of knowledge between humans and machines. It uses YAML frontmatter to map onto YAML-LD, allowing for round-trip conversions between Markdown and RDF. This approach enables business semantics to be integrated into existing wiki systems, and vice versa.

Based on: GitHub - The-Knowledge-Graph-Guys/vault-ld: Vault-LD: an open spec for Markdown vaults as linked data. YAML-LD frontmatter + a shared @context = an RDF knowledge graph. Prose for humans and LLMs, triples for machines. · github.com