はじめに 初めまして。ZENKIGENデータサイエンスチームのはまなすです。正式な所属はDeNAデータ本部AI技術開発部なのですが[1]、業務委託という形で今年度から深層学習系の開発等に携わっています。 深層学習界隈では、2017年に衝撃的なタイトル（Attention Is All You Need）の論文が発表されてから早5年半、元出自の機械翻訳タスクを大きく越えて、Transformer関連の技術が様々な領域で用いられる汎用アーキテクチャとして目覚ましく発展し続けています。 今回はそんなTransformerが現時点までにどのように活用されてきたか、また、どのように工夫されてきたかをざっくりと俯瞰し、流れをおさらいする目的の記事になります。本記事の大枠は、2021年時点でのサーベイ論文である A Survey of Transformers に倣いつつ、適宜、2023年2月上旬現在ま
I joined GitLab in October 2015, and left in December 2021 after working there for a little more than six years. While I previously wrote about leaving GitLab to work on Inko, I never discussed what it was like working for GitLab between 2015 and 2021. There are two reasons for this: I was suffering from burnout, and didn't have the energy to revisit the last six years of my life (at that time)I w
Stay updatedGet the latest news about Shuttle features and Rust tips Introduction# In the dynamic landscape of web development, Rust has emerged as a language of choice for building safe and performant applications. As Rust's popularity grows, so does the array of web frameworks designed to harness its strengths. This article compares some of the best Rust frameworks highlighting their respective
Cloudflare Workers + Hono ワークショップ - ServerlessDays Tokyo 2023
Cloudflare Workers + Hono ワークショップ 資料はこちら => workshops.yusuke.run #serverlessdays Yusuke Wada 2023-09-24 ServerlessDays Tokyo 2023 workshops.yusuke.run アジェンダ ワークショップについて Workers イントロダクション Hono イントロダクション 基本編 プロキシ編 Web API編 フルスタック編 AI編 Honoをより深く知る その他 1. ワークショップについて 1.1 対象 対象者 Cloudflareでのアプリケーション作成に興味のある方 Honoを使ってみたい方 フロント、バックエンド問いません 前提条件 Wranglerが動く環境をつくっておく npx wrangler が動く JavaScriptに対する知識があるとよい
Storybook 7.0
Storybook is the gold standard UI workshop environment. It’s used across the industry by teams at Monday.com, The Guardian, Intuit, and many others due to its unparalleled framework compatibility and rich features for development, documentation, and testing. Today, I’m excited to announce Storybook 7 (SB7), our first major release in over two years and by far our largest ever. It includes: ⚡ First
【インターンレポート】グラフベースで、機械学習を用いないニュース記事要約文の hallucination 検出
LINE株式会社は、2023年10月1日にLINEヤフー株式会社になりました。LINEヤフー株式会社の新しいブログはこちらです。 LINEヤフー Tech Blog こんにちは、黒澤友哉と申します。 2022 年 8 月 15 日から 6 週間、LINE株式会社の NLP 開発チーム（現在は NLP チーム）で就業型インターンシップを行ないましたので、その内容を報告していきたいと思います。私は東京大学情報理工学系研究科コンピュータ科学専攻の修士で、自然言語処理を専門としています。所属は谷中研究室です。 0. 概要 本文に入る前に、このレポートの概要を書きます。以下の図はこのインターンレポートの背景と手法をまとめた図です。このレポートでは第 3 章で「言語モデルを用いた要約生成」、「hallucination」、「日本語のグラフ」について説明した後、第 4 章でグラフ生成手順と halluc
An Economy of AI Agents Gillian K. Hadfield* Johns Hopkins Andrew Koh† MIT This version: September 3, 2025 Prepared for the NBER Handbook on the Economics of Transformative AI Abstract In the coming decade, artificially intelligent agents with the ability to plan and ex- ecute complex tasks over long time horizons with little direct oversight from humans may be deployed across the economy. This ch
Code Red: The Business Impact of Code Quality– A Quantitative Study of 39 Proprietary Production Codebases
Code Red: The Business Impact of Code Quality – A Quantitative Study of 39 Proprietary Production Codebases Adam Tornhill CodeScene Malmö, Sweden adam.tornhill@codescene.com Markus Borg RISE Research Institutes of Sweden Lund University Lund, Sweden markus.borg@ri.se ABSTRACT Code quality remains an abstract concept that fails to get traction at the business level. Consequently, software companies
How can neural networks learn the rich internal representations required for difficult tasks such as recognizing objects or understanding language? Yoshua Bengio, Yann LeCun, and Geoffrey Hinton are recipients of the 2018 ACM A.M. Turing Award for breakthroughs that have made deep neural networks a critical component of computing. Research on artificial neural networks was motivated by the observa
Migrated to https://github.com/BurtonQin/Awesome-Rust-Checker. Welcome to contribute there. Updated: 2024-11-21 Table of contents Table of contents Linters Static Checkers Dynamic Checkers Verifiers Linters Name Description Working on Bug types Technology Maintenance clippy A bunch of lints to catch common mistakes and improve your Rust code. Paper: ICSE-Companion’24 HIR Versatile Pattern matching
GitHub - diff-usion/Awesome-Diffusion-Models: A collection of resources and papers on Diffusion Models
DiffEnc: Variational Diffusion with a Learned Encoder Beatrix M. G. Nielsen, Anders Christensen, Andrea Dittadi, Ole Winther arXiv 2023. [Paper] 30 Oct 2023 Upgrading VAE Training With Unlimited Data Plans Provided by Diffusion Models Tim Z. Xiao, Johannes Zenn, Robert Bamler arXiv 2023. [Paper] 30 Oct 2023 Successfully Applying Lottery Ticket Hypothesis to Diffusion Model Chao Jiang, Bo Hui, Boha
自由エネルギー原理 - 脳科学辞典
磯村 拓哉 理化学研究所脳神経科学研究センター DOI：10.14931/bsd.10024 原稿受付日：2022年1月31日 原稿完成日：2022年4月3日 担当編集委員：北城 圭一（生理学研究所） 英：free-energy principle 独：Prinzip der freien Energie 仏：principe de l'énergie libre 自由エネルギー原理は、Karl J. Fristonが提唱している脳の情報理論である。生物の知覚や学習、行動は、変分自由エネルギーと呼ばれるコスト関数を最小化するように決まるとしている。その結果、生物は変分ベイズ推論と呼ばれる統計学的な推論を自己組織化に行うとされている。 背景 生物の感覚入力に基づく適応的な行動は、何らかの自己組織化（つまり適応、最適化）によって特徴付けることができる。生物は、感覚入力を生成する外部環境のダイナ
Annotated history of modern AI and deep neural networks
For a while, DanNet enjoyed a monopoly. From 2011 to 2012 it won every contest it entered, winning four of them in a row (15 May 2011, 6 Aug 2011, 1 Mar 2012, 10 Sep 2012).[GPUCNN5] In particular, at IJCNN 2011 in Silicon Valley, DanNet blew away the competition and achieved the first superhuman visual pattern recognition[DAN1] in an international contest. DanNet was also the first deep CNN to win
Credit for the title image: Liu et al. (2021) 2021 saw many exciting advances in machine learning (ML) and natural language processing (NLP). In this post, I will cover the papers and research areas that I found most inspiring. I tried to cover the papers that I was aware of but likely missed many relevant ones. Feel free to highlight them as well as ones that you found inspiring in the comments.
Exactly ten years ago today, we published "Why We Created Julia", introducing the Julia project to the world. At this point, we have moved well past the ambitious goals set out in the original blog post. Julia is now used by hundreds of thousands of people. It is taught at hundreds of universities and entire companies are being formed that build their software stacks on Julia. From personalized me
It has been twenty years since Valgrind 1.0 was released. The Valgrind website says: Valgrind is an instrumentation framework for building dynamic analysis tools. There are Valgrind tools that can automatically detect many memory management and threading bugs, and profile your programs in detail. You can also use Valgrind to build new tools. – I first met Julian Seward in late 2001. I had moved fr
AI as Normal Technology
A project studying how advanced AI systems may harm, or help strengthen, democratic freedoms We articulate a vision of artificial intelligence (AI) as normal technology. To view AI as normal is not to understate its impact—even transformative, general-purpose technologies such as electricity and the internet are “normal” in our conception. But it is in contrast to both utopian and dystopian vision
精神分析を患う国｜フリー・グーグルトン
■ 20世紀で最も並外れた知的信用詐欺 1960年にノーベル生理学・医学賞を受賞した生物学者、ピーター・メダワーはかつて「精神医学の被害者（Victims of Psychiatry）」と題した書評において、精神分析を「20世紀で最も並外れた知的信用詐欺（the most stupendous intellectual confidence trick of the 20th century）」と表現した。*1書評の対象は、アメリカの神経外科医I.S.クーパーの著作『The victim is always the same』で、変形性筋ジストニア（DMD）の若い患者が、それが神経筋疾患であるにもかかわらず精神疾患と誤診され、フロイト派の精神分析医によって行われる医学的にも倫理的にも不適当な「治療」を受けさせられる悲劇が描かれている。*2 精神医学における精神分析は前世紀半ばまでは隆盛を誇
How We Built Hydrogen: A React Framework for Building Custom Storefronts - Shopify
How We Built Hydrogen: A React Framework for Building Custom StorefrontsWe’ve been building Hydrogen for more than a year. Here’s a look behind the scenes at how we did it, what we learned from making big bets, and what it was like building a new framework from the ground up on experimental technology. We’ve been building Hydrogen, a React framework for building custom storefronts on Shopify, for
RubyKaigi Speakers Source on GitHub Year Name Title 2026 Satoshi Tagomori The Journey of Box Building 2026 Hitoshi HASUMI Funicular: A Browser App Framework Powered by PicoRuby.WASM 2026 Andrey Marchenko When Can You Skip a Test? Tracking Test Impact 2026 ODA Hirohito Back to the roots of date 2026 Yudai Takada Liberating Ruby's Parser from Lexer Hacks 2026 Justin Bowen Million-Agent Ruby: Ractor-
Home > Computer Vision > Mastering All YOLO Models from YOLOv1 to YOLOv12: Papers Explained (2025) What is YOLO? You Only Look Once (YOLO): Unified, Real-Time Object Detection is a single-stage object detection model published at CVPR 2016, by Joseph Redmon, famous for having low latency and high accuracy. The entire YOLO series of models is a collection of pioneering concepts that have shaped tod
111 A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT YIHAN CAO∗, Lehigh University & Carnegie Mellon University, USA SIYU LI, Lehigh University, USA YIXIN LIU, Lehigh University, USA ZHILING YAN, Lehigh University, USA YUTONG DAI, Lehigh University, USA PHILIP S. YU, University of Illinois at Chicago, USA LICHAO SUN, Lehigh University, USA Recen
The Little Book of Deep Learning
The Little Book of Deep Learning François Fleuret François Fleuret is a professor of computer sci- ence at the University of Geneva, Switzerland. The cover illustration is a schematic of the Neocognitron by Fukushima [1980], a key an- cestor of deep neural networks. This ebook is formatted to fit on a phone screen. Contents Contents 5 List of figures 7 Foreword 8 I Foundations 10 1 Machine Learnin
Workshop: An Introduction to macOS Forensics with Open Source Software
Workshop: An Introduction to macOS Forensics with Open Source Software Japan Security Analyst Conference 2022 株式会社インターネットイニシアティブ 小林 稔 Who am I? 小林 稔 2 • 株式会社インターネットイニシアティブ セキュリティ本部 セキュリティ情報統括室 技術調査、社内インシデントレスポンス • 外部活動 セキュリティキャンプ全国大会講師 2017-2019 Japan Security Analyst Conference Speaker 2018/2020 Black Hat USA 2018 Briefing Speaker • Twitter: @unkn0wnbit はじめに 3 0 本ワークショップの目的 (1/2) ◦本ワークショップでやること ▪
Eight Things to Know about Large Language Models Samuel R. Bowman 1 2 Abstract The widespread public deployment of large lan- guage models (LLMs) in recent months has prompted a wave of new attention and engage- ment from advocates, policymakers, and scholars from many fields. This attention is a timely re- sponse to the many urgent questions that this tech- nology raises, but it can sometimes mis
GitHub - ComfyUI-Workflow/awesome-comfyui: A collection of awesome custom nodes for ComfyUI
ComfyUI-Gemini_Flash_2.0_Exp (⭐+172): A ComfyUI custom node that integrates Google's Gemini Flash 2.0 Experimental model, enabling multimodal analysis of text, images, video frames, and audio directly within ComfyUI workflows. ComfyUI-ACE_Plus (⭐+115): Custom nodes for various visual generation and editing tasks using ACE_Plus FFT Model. ComfyUI-Manager (⭐+113): ComfyUI-Manager itself is also a cu
It’s School time! Adventures in hacking kindle | Sam Khawasé
It was Monday and my daughter was late for the school again. To make things worse, the bus came early by 2 minutes. After rushing and making sure she caught the bus on time, I sat down for my morning coffee and opened up Hacker News. The front page had an interesting entry: “All Kindles can now be jailbroken”. Curiously my old kindle was lying next to me. Was this a sign from the universe? There w
latest | Scrum Guide Expansion Pack | Scrum Guide Expansion Pack
based on the original Scrum Guide by Ken Schwaber & Jeff Sutherland (40) Collected Resources for Scrum Guide Expansion Pack This document is a collection of independent works. Each section retains its original license or copyright status, as indicated. Please refer to each section for specific usage rights and requirements. Section 1: Scrum Guide Expansion Pack 1 (Adaptation) Title: Scrum Guide Ex
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
30分で完全理解するTransformerの世界
What it was like working for GitLab
Best Rust Web Frameworks to Use in 2023 | Shuttle
An Economy of AI Agents
Deep Learning for AI – Communications of the ACM
A curated list of awesome Rust checkers
ML and NLP Research Highlights of 2021
Why We Use Julia, 10 Years Later
Twenty years of Valgrind
RubyKaigi Speakers
Mastering All YOLO Models from YOLOv1 to YOLOv12
A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT
Eight Things to Know about Large Language Models