engineering 25
View all
Co-evolving Four Roles, GAN-Style: The Testbed Behind umigame_GAN
Detecting Duplicate Images with dHash and Hamming Distance in a Chrome Extension
Loading 80 Parcels into a Kei Van in Seconds: Extreme Points and an Independent Validator
Finding the Original of a Reposted Image: How Origin Finder Combines Five Reverse Image Searches
Turning a Drawing-Only Part Back into Editable 3D: How image2CAD Keeps Dimensions and History
From 2D Drawings to Editable FreeCAD Models: the image2CAD Pipeline
Building a Talking 3D Character App with FastAPI, TypeScript, VRM and Passkeys
Trend Analysis with Next.js and the YouTube Data API — Designing Filters and Aggregation
A Travel Calendar in Go, Gorilla Mux, and React: How BookingButler Is Built
Inside chatGPT_streamlit: A Search-Enabled Chat UI with Streamlit and LangChain ReAct
Building the TopicDigestX Backend on FastAPI and PostgreSQL
Reversing the Order of House Hunting: Designing a Gym-First Search
Choosing a Home From the Gym Outward: A Go (Gin) + React API for Commute-Aware Search
A LoRA Training Pipeline for Japanese LLMs on MLX: LFM2.5-1.2B-JP
Optimizing a Band Setlist with OR-Tools TSP: Cost Matrices and Break Insertion
A Japanese Voice-Clone TTS Pipeline with TADA, FastAPI, Whisper, and FFmpeg
A Discord Bot That Lives in the Chat: Ollama, discord.js, and a News Pipeline
A Drawing Critique App in Go, SQLite (WAL), React, and an Ollama VLM
How JamSlicer Splits Long Videos with FFmpeg silencedetect
Building a LINE Butler Bot with Gemini Function Calling and MCP
Rediscovering Likes with Similar Images: Next.js, pgvector, DINOv2, and an MV3 Extension
How tsuzukan Tracks Manga Sequels: Go, React 19, and Three Bibliographic APIs
On the use of distributed representations bagging for class classification and generalization performance
Using BART (sentence summary model) with hugging face
I made a summary text generation AI for making short-form news
python 24
View all
Less Time Searching the Cargo Area: A Load Plan That Does Not Cram the Van
Loading 80 Parcels into a Kei Van in Seconds: Extreme Points and an Independent Validator
Folding the Search for a Repost's Origin into One Query
Finding the Original of a Reposted Image: How Origin Finder Combines Five Reverse Image Searches
From 2D Drawings to Editable FreeCAD Models: the image2CAD Pipeline
A Search-Enabled Chat UI in the Shortest Path: A Research Assistant with Streamlit and a ReAct Agent
Inside chatGPT_streamlit: A Search-Enabled Chat UI with Streamlit and LangChain ReAct
Building the TopicDigestX Backend on FastAPI and PostgreSQL
Optimizing a Band Setlist with OR-Tools TSP: Cost Matrices and Break Insertion
Automating the Split of Stream Archives: Three Walls of Manual Work, Memory, and Speed
How JamSlicer Splits Long Videos with FFmpeg silencedetect
How to Efficiently Solve Low Accuracy and High Cost Issues in Japanese Text Generation with T5
Building a python environment with poetry on mac os
Why is fasttext so fast?
Creating data in Natural Language Inference (NLI) format for Sentence transformer
On the use of distributed representations bagging for class classification and generalization performance
How to train a Japanese model with Sentence transformer to get a distributed representation of a sentence
Using BART (sentence summary model) with hugging face
Procedure for obtaining a distributed representation of a Japanese sentence using a trained Universal Sentence Encoder
Enumerating Applications of Document Classification Problems Only
A note on how to use BERT learned from Japanese Wikipedia, now available
How to use NeuralClassifier, a library that provides a crazy number of models for document classification problems
I even did a document classification problem with Fasttext
I made a summary text generation AI for making short-form news
problem solving 19
View all
The Small LLM That Answers Before It Thinks: Four Roles and a Comparison Design
When the Timeline Fills Up with Reposts and Copies: Designing a Filter That Only Changes What You See
Folding the Search for a Repost's Origin into One Query
Turning One Image into a Talking 3D Character: Making the Build Repeatable
Reading Trend Performance in Numbers — Filling the Blind Spot in View-Count Rankings
Stop Calculating Business Trip Travel Time by Hand
A Search-Enabled Chat UI in the Shortest Path: A Research Assistant with Streamlit and a ReAct Agent
Cutting the Cost of Knowing What Is Trending on X
Fine-tuning a Japanese LLM Without a GPU: One Mac, One Pipeline
Three Constraints in Setlist Planning, and How Each One Was Removed
Reading Aloud in My Own Voice: Voice-Clone TTS from 30 Seconds of Audio
Filling a Quiet Discord Channel and a Broken News Flow with One Resident Bot
No One to Critique Your Drawing, and No Wish to Upload It
Automating the Split of Stream Archives: Three Walls of Manual Work, Memory, and Speed
A LINE Butler That Keeps Its Character While Recommending Products
When Your Likes Get Buried: Designing Capture and Rediscovery for X Favorites
Preventing Missed Sequels by Design: Stop Relying on Remembering at the Bookstore
How to Solve Audio File Volume Inconsistency and Quality Unification Issues with ffmpeg Normalization
How to Efficiently Solve Low Accuracy and High Cost Issues in Japanese Text Generation with T5
machine learning 12
View all
How to Efficiently Solve Low Accuracy and High Cost Issues in Japanese Text Generation with T5
Why is fasttext so fast?
Creating data in Natural Language Inference (NLI) format for Sentence transformer
On the use of distributed representations bagging for class classification and generalization performance
How to train a Japanese model with Sentence transformer to get a distributed representation of a sentence
Using BART (sentence summary model) with hugging face
Procedure for obtaining a distributed representation of a Japanese sentence using a trained Universal Sentence Encoder
Enumerating Applications of Document Classification Problems Only
A note on how to use BERT learned from Japanese Wikipedia, now available
How to use NeuralClassifier, a library that provides a crazy number of models for document classification problems
I even did a document classification problem with Fasttext
I made a summary text generation AI for making short-form news
natural language processing 11
View all
How to Efficiently Solve Low Accuracy and High Cost Issues in Japanese Text Generation with T5
Why is fasttext so fast?
Creating data in Natural Language Inference (NLI) format for Sentence transformer
How to train a Japanese model with Sentence transformer to get a distributed representation of a sentence
Using BART (sentence summary model) with hugging face
Procedure for obtaining a distributed representation of a Japanese sentence using a trained Universal Sentence Encoder
Enumerating Applications of Document Classification Problems Only
A note on how to use BERT learned from Japanese Wikipedia, now available
How to use NeuralClassifier, a library that provides a crazy number of models for document classification problems
I even did a document classification problem with Fasttext
I made a summary text generation AI for making short-form news
technology 11
View all
How to Efficiently Solve Low Accuracy and High Cost Issues in Japanese Text Generation with T5
Creating data in Natural Language Inference (NLI) format for Sentence transformer
On the use of distributed representations bagging for class classification and generalization performance
How to train a Japanese model with Sentence transformer to get a distributed representation of a sentence
Using BART (sentence summary model) with hugging face
Procedure for obtaining a distributed representation of a Japanese sentence using a trained Universal Sentence Encoder
Enumerating Applications of Document Classification Problems Only
A note on how to use BERT learned from Japanese Wikipedia, now available
How to use NeuralClassifier, a library that provides a crazy number of models for document classification problems
I even did a document classification problem with Fasttext
I made a summary text generation AI for making short-form news
react 10
View all
Stop Calculating Business Trip Travel Time by Hand
A Travel Calendar in Go, Gorilla Mux, and React: How BookingButler Is Built
A Search-Enabled Chat UI in the Shortest Path: A Research Assistant with Streamlit and a ReAct Agent
Inside chatGPT_streamlit: A Search-Enabled Chat UI with Streamlit and LangChain ReAct
Reversing the Order of House Hunting: Designing a Gym-First Search
Choosing a Home From the Gym Outward: A Go (Gin) + React API for Commute-Aware Search
A Drawing Critique App in Go, SQLite (WAL), React, and an Ollama VLM
How JamSlicer Splits Long Videos with FFmpeg silencedetect
Preventing Missed Sequels by Design: Stop Relying on Remembering at the Bookstore
How tsuzukan Tracks Manga Sequels: Go, React 19, and Three Bibliographic APIs
fastapi 8
View all
Finding the Original of a Reposted Image: How Origin Finder Combines Five Reverse Image Searches
Building a Talking 3D Character App with FastAPI, TypeScript, VRM and Passkeys
Cutting the Cost of Knowing What Is Trending on X
Building the TopicDigestX Backend on FastAPI and PostgreSQL
Reading Aloud in My Own Voice: Voice-Clone TTS from 30 Seconds of Audio
A Japanese Voice-Clone TTS Pipeline with TADA, FastAPI, Whisper, and FFmpeg
Automating the Split of Stream Archives: Three Walls of Manual Work, Memory, and Speed
How JamSlicer Splits Long Videos with FFmpeg silencedetect
go 8
View all
Stop Calculating Business Trip Travel Time by Hand
A Travel Calendar in Go, Gorilla Mux, and React: How BookingButler Is Built
Reversing the Order of House Hunting: Designing a Gym-First Search
Choosing a Home From the Gym Outward: A Go (Gin) + React API for Commute-Aware Search
No One to Critique Your Drawing, and No Wish to Upload It
A Drawing Critique App in Go, SQLite (WAL), React, and an Ollama VLM
Preventing Missed Sequels by Design: Stop Relying on Remembering at the Bookstore
How tsuzukan Tracks Manga Sequels: Go, React 19, and Three Bibliographic APIs
distributed representation 7
View all
Why is fasttext so fast?
On the use of distributed representations bagging for class classification and generalization performance
How to train a Japanese model with Sentence transformer to get a distributed representation of a sentence
Using BART (sentence summary model) with hugging face
Procedure for obtaining a distributed representation of a Japanese sentence using a trained Universal Sentence Encoder
A note on how to use BERT learned from Japanese Wikipedia, now available
I even did a document classification problem with Fasttext
llm 7
View all
The Small LLM That Answers Before It Thinks: Four Roles and a Comparison Design
Co-evolving Four Roles, GAN-Style: The Testbed Behind umigame_GAN
Inside chatGPT_streamlit: A Search-Enabled Chat UI with Streamlit and LangChain ReAct
Cutting the Cost of Knowing What Is Trending on X
Fine-tuning a Japanese LLM Without a GPU: One Mac, One Pipeline
A LoRA Training Pipeline for Japanese LLMs on MLX: LFM2.5-1.2B-JP
A Discord Bot That Lives in the Chat: Ollama, discord.js, and a News Pipeline
typescript 7
View all
Building a Talking 3D Character App with FastAPI, TypeScript, VRM and Passkeys
Reading Trend Performance in Numbers — Filling the Blind Spot in View-Count Rankings
Trend Analysis with Next.js and the YouTube Data API — Designing Filters and Aggregation
A Travel Calendar in Go, Gorilla Mux, and React: How BookingButler Is Built
A Discord Bot That Lives in the Chat: Ollama, discord.js, and a News Pipeline
How JamSlicer Splits Long Videos with FFmpeg silencedetect
Building a LINE Butler Bot with Gemini Function Calling and MCP
postgresql 5
View all
Building the TopicDigestX Backend on FastAPI and PostgreSQL
Choosing a Home From the Gym Outward: A Go (Gin) + React API for Commute-Aware Search
Rediscovering Likes with Similar Images: Next.js, pgvector, DINOv2, and an MV3 Extension
Preventing Missed Sequels by Design: Stop Relying on Remembering at the Bookstore
How tsuzukan Tracks Manga Sequels: Go, React 19, and Three Bibliographic APIs
chrome-extension 4
View all
When the Timeline Fills Up with Reposts and Copies: Designing a Filter That Only Changes What You See
Detecting Duplicate Images with dHash and Hamming Distance in a Chrome Extension
When Your Likes Get Buried: Designing Capture and Rediscovery for X Favorites
Rediscovering Likes with Similar Images: Next.js, pgvector, DINOv2, and an MV3 Extension
ffmpeg 4
View all
A Japanese Voice-Clone TTS Pipeline with TADA, FastAPI, Whisper, and FFmpeg
Automating the Split of Stream Archives: Three Walls of Manual Work, Memory, and Speed
How JamSlicer Splits Long Videos with FFmpeg silencedetect
How to Solve Audio File Volume Inconsistency and Quality Unification Issues with ffmpeg Normalization
subculture science research group 4
View all
Subculture Science Research Group the 6th meeting: What is the point of football viewing?
Subculture Science Research Group the 5th meeting NFT
The 4th Regular Meeting of the Subculture Science Research Group: Sake and Wood
Subculture Science Research Group Regular Meeting No.3 Wood for electric guitar or anything else?