LLM
Hello! The "Deep Research" scene has suddenly been heating up. Today, we dive into Open Deep Research—announced just yesterday (February 5, 2025)—and walk through its architecture and implementation! 1. Introduction OpenAI's "GPT Deep Research" has been making waves, and it seems likely
Daily Dev Tips
Hello! In this article, we look at UUID generation in Node.js, a mainstay of modern web front ends—specifically, howcrypto.randomUUID()differs from the traditional approach. Introduction UUIDs are widely used as unique identifiers, and Node.js offers more than one way to generate them. How to Use crypto.
AI Mathematics
Hello! Today I'd like to explain EMA*, which plays an important role in image generation, video generation, and other models. It also serves us well in MotionVox™, our AI avatar video generation service. That said, EMA is not a technique exclusive to image generation. It has become a
AI Mathematics
Hello from the Qualiteg Research Team! Today we explain Direct Preference Optimization (DPO)—proposed in 2023 by the research team of Rafael Rafailov, Archit Sharma, and colleagues—from the fundamentals through to its applications. The method was introduced in the paper "Direct Preference Optimization: Your Language Model is Secretly
Daily Dev Tips
Hello! Today we look at a surprisingly common mystery error caused by packages you don't remember installing, and what turns out to be behind it. The environment in this case was Windows with Python and Anaconda installed, but the same essentially applies to Linux as well. It turned
Daily Dev Tips
Hello! This post is a note on how to install Windows Terminal on the Windows Server 2022 Datacenter edition. Doing it step by step was a bit of a hassle, so I turned the whole procedure into a script you can simply paste into PowerShell to install everything automatically. Paste
Daily Dev Tips
In Windows 11, the right-click menu has been simplified, hiding convenient items such as "Send to". In this article, we show you how to restore the classic Windows 10-style menu. [Note] Registry changes must be made with care, and incorrect operations may affect your system. We recommend backing
NumPy/PyTorch
Hello! Today's topic is optimization, an essential step when taking an AI application developed with PyTorch to production. Specifically, we will look at optimizing various trained models using TorchScript. TorchScript Basics 1 What Is TorchScript? TorchScript is a technology that converts PyTorch models into an optimized intermediate representation
NumPy/PyTorch
Hello! Today we are covering in-place operations in PyTorch. When building deep learning models, memory management becomes a major challenge. For many of you, the biggest part of that challenge is probably GPU memory. This is where PyTorch's in-place operations come to the rescue. In this article, we
IT & AI Technology
Hello! This is the Qualiteg Research Team! Today we would like to talk about image generation technology. As many of you know, AI-based image generation technology has evolved rapidly over the past decade. It is now 2024—exactly ten years since GANs were introduced in 2014. While text-based generative AI
ChatStream Guide
chatstream.net is a service operated by Qualiteg Inc. that lets you try out the latest publicly available LLMs from around the world as soon as they are released. You can open a particular LLM for an in-depth chat, open several LLMs and use them together, or have LLMs compare
NumPy/PyTorch
Hello! Today we address one of the questions we hear most often: "Can a single model instance safely run parallel inference?" Safety of Parallel Inference in eval Mode When a PyTorch model has been set to eval mode using model.eval(), it is generally safe for parallel inference.
NumPy/PyTorch
Hello! Today, let's take a look at vertically merging arrays in NumPy. As you know, NumPy is a powerful library for scientific computing in Python. We will walk through five different approaches to vertically merging multiple NumPy arrays into a single larger array. Specifically, we will look at
NumPy/PyTorch
Introduction Hello! This is the Qualiteg Product Development Team. At Qualiteg, we research and develop AI characters and AI humans built on LLM technology. When reproducing virtual humans with "human-like" qualities such as facial expressions and gestures, AI-powered image processing—image generation and image editing—becomes essential. AI
PyTorch
Companies with legacy PyTorch codebases often run into problems like "our old code doesn't run on the latest PyTorch" or "it doesn't run on the latest GPUs (such as the GeForce RTX 50 series, i.e., Blackwell)." In this article, we organize
![Tensor Operations Worth Mastering: tensor.unsqueeze(0) vs. array[None]](https://images.unsplash.com/photo-1618912617207-0c06851b2dc9?crop=entropy&cs=tinysrgb&fit=max&fm=jpg&ixid=M3wxMTc3M3wwfDF8c2VhcmNofDQ1fHxzcXVlZXplfGVufDB8fHx8MTcyNjExNjYxNHww&ixlib=rb-4.0.3&q=80&w=600)
NumPy/PyTorch
Today we will walk through unsqueeze(0), and along the way touch on a familiar problem many of us run into. Can you tell "value.unsqueeze(0)" and "value[None]" apart at a glance? The former is primarily a PyTorch operation, while the latter belongs to