The official Pytorch implementation of "Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors". [ICASSP 2024] and "LS-EEND: long-form streaming end-to-end neural diarization with online attractor extraction". [TASLP 2025]

Your YouTube channel, encoded. A team of agents running ideation, hooks, retention, scripts, thumbnails, and distribution. Runtime agnostic.

Official repository for the paper: Can AI Agents Synthesize Scientific Conclusions?

A SillyTavern extension for immersive long-form reading with better typography and layout.

Wolfram Language (aka Mathematica) paclet for data reshaping functions, like, long- and wide form, cross tabulation, etc.

长文小说肌肉记忆写作法 - Long-form Novel Writing Skill using Muscle Memory Methodology

Under the Code — a unified theory of how computers actually work. Five parts, eighteen chapters, ~93,000 words, 200+ inline-SVG figures. Visual-first, history-anchored, security as backbone. Static site (HTML + CSS + JS, no framework) deploying from public/. Live at under.atheric.eu.

A nostr blogging platform

Vibe-Blog是一个基于Multi-Agent 架构的万字长文技术博客生成AI助手，支持深度调研、智能配图、Mermaid 图表、代码集成、专业排版的各种专业技术博客写作中所需要的能力, 真正做到了 "输入一句话, 一键输出图文混合的万字技术长文, 轻轻松松做到日更万字长文技术博客"，将晦涩的技术知识转化为通俗易懂的科普文章，让每个人都能轻松理解复杂技术,在 AI 时代扬帆起航.

Turn any topic into multi-part NotebookLM podcasts with music, plus a prompt+transcript+diarization dataset. Built with Claude Code.

An open format for the dynamic attention category — long-form text + reader-led narration + sovereign ambient music

A repository holding long form stories generated with getmural.io

This repo explores token classification for abbreviation and long-form detection using RoBERTa. We evaluate the impact of adding 50% of the PLODv2-filtered dataset, achieving improved F1 and recall. The repo includes methodology, evaluation using seqeval, and confusion matrix analysis.