Language Model

Auto Added by WPeMatico

Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026

ai, AI (Artificial Intelligence), Artificial Intelligence, Editors Pick, Language Model, OCR, Open Source, Software engineering, Staff, Technology, Top

Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents cannot use that data until it becomes structured JSON. Open-source document extraction has become the standard way to do that conversion on your own hardware. Two different problems hide under the phrase ‘PDF to JSON.’ The first is schema-driven […]

Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026 Read More »

Anthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines

agentic ai, ai, AI (Artificial Intelligence), Applications, Artificial Intelligence, Editors Pick, Language Model, Software engineering, Staff, Tech News

This week, Anthropic released Claude Science. It is an app for scientists, available in beta. It runs on Anthropic’s existing Claude models, not a new model. The app targets researchers who juggle databases, notebooks, and cluster terminals. It runs multi-step research and records how each result was made. The beta is available for Pro, Max,

Anthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines Read More »

NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Software engineering, Staff, Tech News, Technology

NVIDIA Research introduced HORIZON, a hands-free agent framework for hardware design. It treats hardware design as repository-level code evolution. This research team exercises the register-transfer level (RTL) instantiation. A structured Markdown harness becomes a project pack. A self-contained agent loop then evolves an isolated git worktree. It commits a version only when an executable acceptance

NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion Read More »

Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems

agentic ai, ai, AI (Artificial Intelligence), AI Agents, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Software engineering, Staff, Tech News, Technology, Uncategorized

Today, Mistral AI released Leanstral 1.5. It is a code agent model built for Lean 4. The release targets automated theorem proving and proof engineering. Weights are open under Apache 2.0. A free API endpoint, leanstral-1-5, is now live. Leanstral 1.5 updates the earlier Leanstral-2603 model. It belongs to the Mistral Small 4 family. What

Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems Read More »

Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model Transcribing Six Languages via DiffusionGemma’s Parallel Denoising Decoder

ai, AI (Artificial Intelligence), Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, New Releases, Open Source, Technology, TTS, Voice AI

Interfaze, a young YC’s startup, has open-sourced a new speech recognition model. It is called diffusion-gemma-asr-small. The model transcribes audio through a diffusion decoder, not an autoregressive one. It is described as the first multilingual audio diffusion ASR model. One adapter handles six languages. The research team trained only about 42M parameters on top of

Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model Transcribing Six Languages via DiffusionGemma’s Parallel Denoising Decoder Read More »

RAG-Anything Tutorial: Build a Multimodal Retrieval Pipeline for Text, Tables, Equations, and Images in Colab

ai, AI (Artificial Intelligence), Applications, Artificial Intelligence, Editors Pick, Language Model, RAG, Staff, Technology, Tutorials

In this tutorial, we build a RAG-Anything workflow and use it to explore how multimodal retrieval works across text, tables, equations, and images. We start by preparing the Colab environment, installing the required packages, and securely entering our OpenAI API key at runtime to keep the notebook practical and safe to run. We then create

RAG-Anything Tutorial: Build a Multimodal Retrieval Pipeline for Text, Tables, Equations, and Images in Colab Read More »

Using Lift to Turn Research PDFs into Structured JSON with Controlled, Schema-Guided Field-Level Evaluation

ai, AI (Artificial Intelligence), Applications, Artificial Intelligence, Editors Pick, Language Model, OCR, Staff, Technology, Tutorials

In this tutorial, we build a complete PDF-to-structured-data extraction workflow around Lift, with a focus on controlled evaluation rather than a simple demo run. We begin by preparing a Colab-compatible GPU environment, selecting the appropriate precision mode for the available hardware, and patching model loading to ensure the Lift backend runs reliably even on constrained

Using Lift to Turn Research PDFs into Structured JSON with Controlled, Schema-Guided Field-Level Evaluation Read More »

NVIDIA Releases Nemotron-Labs-TwoTower: an Open-Weight Diffusion Language Model Built on a Frozen Autoregressive Nemotron-3-Nano-30B-A3B Backbone

ai, AI (Artificial Intelligence), AI Paper Summary, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Staff, Tech News, Technology

NVIDIA has released Nemotron-Labs-TwoTower, a diffusion language model built on a pretrained autoregressive backbone. It ships as open weights under the NVIDIA Nemotron Open Model License. The release targets a throughput bottleneck in text generation. Autoregressive (AR) models decode one token at a time. That serial process caps generation throughput. Discrete diffusion language models take

NVIDIA Releases Nemotron-Labs-TwoTower: an Open-Weight Diffusion Language Model Built on a Frozen Autoregressive Nemotron-3-Nano-30B-A3B Backbone Read More »

Anthropic Claude Sonnet 5 vs Sonnet 4.6 vs Opus 4.8: Agentic Coding Benchmarks, API Pricing, and Cost-Performance Tradeoffs Compared

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, New Releases, Software engineering, Staff, Tech News, Technology

Anthropic just shipped Claude Sonnet 5. They call it its most agentic Sonnet model yet. It plans, drives browsers and terminals, and runs autonomously across long tasks. Sonnet 5 is the default model for Free and Pro plans today. Max, Team, and Enterprise users can select it. It is also live in Claude Code and

Anthropic Claude Sonnet 5 vs Sonnet 4.6 vs Opus 4.8: Agentic Coding Benchmarks, API Pricing, and Cost-Performance Tradeoffs Compared Read More »

NVIDIA BioNeMo Agent Toolkit Turns Biomolecular Models Into Callable Skills for AI Agents in Drug Discovery

AI scientists are becoming a new interface for scientific computing. These agents read papers, write code, generate hypotheses, call APIs, and inspect files. But science is not software engineering. No test suite turns green when a hypothesis is correct. Discovery stays iterative, uncertain, and grounded in the physical world. That gap is what NVIDIA is

NVIDIA BioNeMo Agent Toolkit Turns Biomolecular Models Into Callable Skills for AI Agents in Drug Discovery Read More »