Editors Pick

Auto Added by WPeMatico

Developing an End-to-End Document Intelligence Pipeline with docTR for OCR, Layout Analysis, KIE, Benchmarking, and Searchable PDFs

ai, AI (Artificial Intelligence), Artificial Intelligence, Computer vision, Editors Pick, Technology, Tutorials

In this tutorial, we develop an end-to-end OCR workflow with docTR and explore how modern document understanding pipelines combine text detection, recognition, geometry, layout analysis, structured extraction, and export. We generate realistic synthetic invoice documents, load images and PDFs through DocumentFile, construct GPU-aware OCR predictors, and benchmark different detection–recognition architecture combinations for speed and accuracy. […]

Developing an End-to-End Document Intelligence Pipeline with docTR for OCR, Layout Analysis, KIE, Benchmarking, and Searchable PDFs Read More »

DeepSeek AI Releases DeepSeek Harness in Developer Preview: An MIT-Licensed Agent Harness Where Everything is a Plugin

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

DeepSeek released DeepSeek Harness v0.1 in developer preview and published the full source code under the MIT license. The project ships as dsh at deepseek-ai/deepseek-harness. A harness is the layer between a model and the environment it acts in — the tools, files, sandboxes, and control loop that let an agent keep working. DeepSeek frames

DeepSeek AI Releases DeepSeek Harness in Developer Preview: An MIT-Licensed Agent Harness Where Everything is a Plugin Read More »

Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3

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

In this tutorial, we implement an end-to-end supervised fine-tuning pipeline for the XYZ-Aquila-SFT dataset, Hugging Face Transformers, PyTorch, and PEFT. We stream and inspect the dataset, parse multi-turn tool-use trajectories, extract structured tool calls, analyze corpus characteristics, and preserve embedded reasoning and observation patterns. We then convert tool schemas between message-embedded and structured formats, render

Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3 Read More »

Z.ai Ships GLM-5.3 Without Retraining the Base Model: Better at Complex Coding and Long-Horizon Tasks

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

Z.ai just released GLM-5.3. GLM-5.3 runs on the same 743B base model as GLM-5.2. Every reported gain comes from scaled post-training: more task environments, more environment types, longer training. The results land in two places. Coding jumps most on the longest-horizon benchmarks, with Terminal-Bench 3.0 moving from 4.6 to 28.3. Cybersecurity moved further than Z.ai

Z.ai Ships GLM-5.3 Without Retraining the Base Model: Better at Complex Coding and Long-Horizon Tasks Read More »

Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM

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

Cactus Compute has released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The entire model ships as a single 14MB binary that runs a full session in about 28MB of RAM. Weights are trained and deployed at CQ2-bit using Cactus Quants, and the model is sealed inside the company’s

Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM Read More »

Create a Reasoning-Focused LLM: A Practical Guide to Streaming, Curating, and Fine-Tuning the SupraLabs Reasoning Corpus

ai, AI (Artificial Intelligence), Applications, Artificial Intelligence, Editors Pick, Language Model, Small Language Model, Technology, Tutorials, Uncategorized, Vision Language Model

In this tutorial, we build an end-to-end workflow for working with the SupraLabs reasoning corpus. We stream a representative subset directly from the Hugging Face Hub, inspect its source distribution, token-length patterns, task composition, and reasoning-to-answer ratios, and then apply a series of quality filters to remove unsuitable training examples. We transform the retained samples

Create a Reasoning-Focused LLM: A Practical Guide to Streaming, Curating, and Fine-Tuning the SupraLabs Reasoning Corpus Read More »

Google AI Just Released Gemini 3.7 Flash: A Coding and Agent Model at $0.75/1M Input Tokens

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

Google has released Gemini 3.7 Flash, the newest model in its Flash tier, three weeks after Gemini 3.6 Flash. The model card describes it as a refinement of 3.6 Flash with algorithmic improvements to the core reasoning foundation — not a new pretraining run. It accepts text, images, audio, and video across a 1M-token context

Google AI Just Released Gemini 3.7 Flash: A Coding and Agent Model at $0.75/1M Input Tokens Read More »

Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device

ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Computer vision, Editors Pick, Language Model, Large Language Model, New Releases, OCR, Open Source, Staff, Tech News, Technology, Uncategorized, Vision Language Model

Yesterday, Liquid AI released LFM2.5-VL-3B. It is a 3.1B-parameter vision-language model built for on-device deployment. The model reads digital screens across mobile, web, and desktop. It grounds objects to coordinates, parses documents and charts, and calls tools from text or image input. Liquid AI reports an average of 69.4 across 28 vision benchmarks. That matches

Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device Read More »

▶

Dyna Robotics Introduces Dyna-2: A World-Action Model Pre-Trained on 1 Million Hours of Human Video

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Embedding Model, Language Model, Large Language Model, Machine Learning, New Releases, physical ai, Robotics, Staff, Tech News, Technology, Vision Language Model, World Model

Dyna Robotics has released Dyna-2, a world-action model for robot manipulation. It was pre-trained on more than one million hours of egocentric human video. That is roughly 170 years of continuous waking experience. Robot learning has been bottlenecked by action-labelled data, which teleoperation must deliberately produce. Dyna-2 tests whether ordinary human video can substitute. The

Dyna Robotics Introduces Dyna-2: A World-Action Model Pre-Trained on 1 Million Hours of Human Video Read More »

SpaceXAI Releases Grok 4.6: A 500K-Context Frontier Model Tuned for Long-Running Agents, Coding, and Knowledge Work

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

SpaceXAI just released Grok 4.6. The release is a post-training upgrade over Grok 4.5 rather than a larger base model. SpaceXAI held the foundation constant and spent the improvement on a longer supplemental training run, regenerated supervised fine-tuning trajectories, and reinforcement learning in agentic environments. Agents that stay on a task across many steps without

SpaceXAI Releases Grok 4.6: A 500K-Context Frontier Model Tuned for Long-Running Agents, Coding, and Knowledge Work Read More »