olmOCR proposes plain-text PDF extraction
In a February 25, 2025 post, AllenAI introduced olmOCR, an open-source tool for extracting plain text from PDFs, described as handling various document types and running on a GPU.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
Expressive TTS beta and cross-platform local launcher
On February 15, 2025, a post announced a beta for expressive speech synthesis with voice cloning, Transformer and SSM-hybrid models under Apache 2.0, and a one-click launcher for Mac, Windows, and Linux.
Read articleHibiki: streaming speech translation
Published on February 6, 2025, Hibiki is described as a decoder-only model for simultaneous speech translation between French and English, trained on synthetic data.
Read articleMoonshine integrated into Transformers
A January 20, 2025 post announces integration of the Moonshine automatic speech recognition model with Transformers and highlights support for audio of any duration.
Read articleHPAC-IDS applies hierarchical attention to intrusion detection
Published on January 14, 2025, the summary describes a method that segments raw network packets and uses hierarchical structures and self-attention. Experiments on CIC-IDS2017 report high accuracy, few false positives, and adversarial resilience.
Read articleVideoRAG retrieves videos for multimodal answers
Published on January 14, 2025, this brief describes VideoRAG, a KAIST research framework that retrieves videos relevant to queries and combines visual and textual information in generated answers.
Read articlePiper: locally run neural speech synthesis
Piper converts text to speech with multiple voices, phonemization libraries, multilingual support, and customizable options. Engineers can evaluate it as a local text-to-speech alternative.
Read articleTheAgentCompany assesses agents on workplace tasks
Published on December 19, 2024, TheAgentCompany is presented as a benchmark for assessing AI agents on software development, project management, administration, and data science tasks. The material provides no results or scores.
Read articleGraphiti explores temporal knowledge graphs
Published on December 10, 2024, this entry presents Graphiti as a tool for creating and querying dynamic graphs that represent relationships between entities over time.
Read articleAuto-RAG automates iterative retrieval in RAG systems
Published on December 2, 2024, the post describes a method that plans searches and refines queries across multiple interactions, adjusting the number of iterations to the question's difficulty.
Read articleHijackRAG explores injected text attacks on RAG systems
Published on December 1, 2024, the post presents HijackRAG, an attack that manipulates RAG systems through retrieved content, attention diversion, and instructions.
Read articleRARe adapts retrieval models with retrieved examples
Published on December 1, 2024, the report presents RARe, which adds instructions and semantically similar query-document pairs retrieved with BM25 to retrieval models. The post says similar examples outperformed random ones, with gains increasing as the number of examples rose, up to the 10 tested.
Read articleAssistRAG separates memory from generation
Published on November 30, 2024, AssistRAG proposes managing memory and external knowledge without retraining the main model that generates answers.
Read articleLazyGraphRAG combines vector and graph retrieval
A post published on November 29, 2024 describes an approach combining vector RAG with iterative breadth-first and best-first search, without index summarization. It identifies possible uses and trade-offs for assessing alternatives to full GraphRAG.
Read articleNotebook demos RAG with PDFs
Published on November 28, 2024, the notebook presents a recipe for retrieval-augmented generation over PDF files using Docling and Weaviate. Docling is described as an open-source Python package that converts documents to Markdown or JSON.
Read articleDeepSpeed Domino for distributed LLM training
A post published on November 26, 2024 presents Domino as a tensor-parallelism mechanism intended to reduce communication overhead in LLM training.
Read articleAutoflow combines Graph RAG and TiDB Serverless
A post dated November 22, 2024 describes Autoflow as a conversational knowledge base built on Graph RAG, using TiDB Serverless for vector storage.
Read articleOpenScholar releases code, models, and research corpus
On November 19, 2024, the OpenScholar project announced code, model checkpoints, a corpus of over 45 million papers, and the ScholarQABench benchmark.
Read articleUltravox: a multimodal model for real-time voice
Published on November 18, 2024, this entry presents Ultravox as a fast multimodal LLM for real-time voice. It says the source code is available on GitHub for examining and assessing its approach.
Read articleKAR expands queries with knowledge graphs
Published on November 13, 2024, this entry describes a workflow using model-extracted entities, relevant documents, and knowledge-graph relations to generate context-aware query expansions.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.