Stars
📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
🧡 Browser extension that simplifies finding and subscribing RSS and RSSHub
🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image c…
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault
AI chat assistant for Obsidian with contextual awareness, smart writing assistance, and one-click edits. Features vault-aware conversations, semantic search, and local model support.
DeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundation.
A python package to train & evaluate Customer Lifetime Value(CLTV) models using Neural Networks & ZILN loss(developed by google)
Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision
A unified architecture deep learning framework designed specifically for ultra-large-scale sparse models.
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
OneTrans from ByteDance. (Tensorflow)
The unofficial implementation of "RankMixer: Scaling Up Ranking Models in Industrial Recommenders"
[KDD 2026] FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction
在常规推荐系统算法和系统双优化的范式下，一线公司针对单个任务或单个业务的效果挖掘几乎达到极限。从2019年我们开始关注多种信息的萃取融合，提出了OneRec算法，希望通过平台或外部各种各样的信息来进行知识集成，打破数据孤岛，极大扩充推荐的“Extra World Knowledge”。 已实践的算法包括行为数据，内容描述，社交信息，知识图谱等。在OneRec，每种信息和整体算法的集成是可插拔…
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
"Exploring Scaling Laws of CTR Model for Online Performance Improvement." In Proceedings of RecSys '25.
将gpt_academic的arxiv论文翻译单独抽取出来，并集成BabelOCR，支持本地PDF翻译，翻译成功率提高到95%+
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
[ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
Awesome Generative Recommendation papers primarily focused on industry-level applications.
An easy-to-use framework for large scale recommendation algorithms.
SASRec: Self-Attentive Sequential Recommendation