Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
Press releases about our workshop, “The 2nd Workshop on Foundation Data for Industrial Tech Transfer (FOUND)” at ECCV 2026, have been published by LY Corporation, CADDi, and SB Intuitions.
-
We will present the following papers at YANS 2026: 陳 冠帆, 川田 拓朗, 守田 竜梧, 北田 俊輔, 彌冨 仁.
-
We will present the following papers at MIRU 2026: Shunsuke Kitada, Shoma Iwai, Ryota Yoshihashi, Atsuki Osanai.
-
第67回 コンピュータビジョン勉強会＠関東（前編） デザイン素材収集と、Photoshopの操作履歴から学習した Vision and Language Model (VLM) によるツール呼び出しの計画・実行を組み合わせ、Agentic に複雑なレイヤー構造をもつ編集可能なデザインを生成する PSDesigner について紹介します。
-
We are happy to announce that our workshop proposal for the 2nd FOUND Workshop, “FOUND: Foundation Data for Industrial Tech Transfer @ ECCV 2026”, has been accepted!
-
Our workshop proposal for the 2nd FOUND Workshop, “FOUND: Foundation Data for Industrial Tech Transfer @ ECCV 2026”, has been accepted at ECCV 2026.
-
Speaker Deck 大規模言語モデル（LLM）の内部状態は、高次元の活性化ベクトルとして表現されており、モデルの推論・判断・潜在的な認識に関する豊かな情報を含んでいます。
-
The following papers have been accepted to the ACL 2026 Student Research Workshop (SRW).
-
【Sansan × IVRy】NLP2026 参加報告会 大規模言語モデル（LLM）に対する内部介入（steering / intervention）は、重み更新を伴わずに推論時の振る舞いを制御できる手法として、近年急速に注目を集めています。
-
Journal Club 大規模言語モデル（LLM）に強化学習を組み合わせた「Agentic RL」は，自律的な意思決定や動的な環境適応能力により，人工知能の新たなフロンティアを切り開いています。
-
We will present the following papers at ANLP 2026: 川田 拓朗, 北田 俊輔, 彌冨 仁.
-
The following papers have been accepted to the Findings of CVPR 2026: Takuro Kawada, Shunsuke Kitada, Sota Nemoto, Hitoshi Iyatomi.
-
Journal Club A Speaker Deck presentation about steering vectors for LLM internal representations.
-
As your number of repositories grows through git clone, for both work and personal projects, it becomes harder to remember where you cloned things and which directory you’re currently working in.
-
Our Paper and Workshop Accepted at ICCV 2025, the Top International Conference on Computer Vision (Participation Report) Hello, I’m Shunsuke Kitada (@shunk031), and I work at LY Corporation on research and development for image generation and design gener…
-
堅牢.py #1 堅牢.py はPythonを安全に扱うための技術に興味を持つエンジニアのイベントです。
-
We will present the following paper at IBIS 2025: 永井 大地, 守田 竜梧, 北田 俊輔, 彌冨 仁.
-
Table of Contents Introduction The difficulty of a dynamically typed language What are type hints?
-
This article explains an approach to dotfiles management that emphasizes testability, using the author’s dotfiles repository shunk031/dotfiles as a case study.
-
We are happy to announce that our workshop proposal for the FOUND Workshop, “FOUND: Foundation Data for Industrial Tech Transfer @ ICCV 2025”, has been accepted!
-
We will present the following papers at YANS 2025: 陳 冠帆, 田中 優太朗, 中川 翼, 北田 俊輔, 川田 拓朗, 彌冨 仁.
-
Journal Club AI技術はグラフィックデザインの領域に革命をもたらし、クリエイティブなプロセスを根本から変えようとしています。
-
We will present the following papers at MIRU 2025: 川田 拓朗, 北田 俊輔, 根本 颯汰, 彌冨 仁.
-
Journal Club 大規模言語モデル（LLM）を搭載した「LLMエージェント」は、自律的な目標達成や動的な環境適応能力により、人工知能の新たなフロンティアを切り開いています 。
-
I’m thrilled to announce that, in addition to my main role at LYCorp., I’ve just started as an part-time researcher at The University of Electro-Communications!
-
Our workshop proposal “FOUND: Foundation Data for Foundation Models” has been accepted at ICCV 2025, one of the top conferences in computer vision.
-
I’m thrilled to announce the release of my new book, “Image Generation with Python”!
-
We will present the following paper at ANLP 2025: 川田 拓朗, 根本 颯汰, 北田 俊輔, 彌冨 仁.