AI-powered campaign generator (video + creative + automation + optimization)

Memory infrastructure for AI agents: store, recall by meaning or association, ingest documents, and track beliefs in one Python library.

A clean, object-oriented implementation of a sponsored search auction engine

TradingAgents: Multi-Agents LLM Financial Trading Framework

Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台…

generative retrieval via hash functions

Offline LLM pipeline configuration, retrieval, and evaluation prototype

Hybrid retrieval (dense + generative on semantic IDs) with full-catalog eval protocol — a from-scratch rewrite with no dependency on SIDA.

Generative Retrieval/Generative Recommendation develop skills for coding agents

End-to-end recommender systems portfolio: multi-stage session recommendation and Semantic ID generative retrieval

Build, train, and evaluate generative recommender systems

React-OT is a generative transition state search model developed by DeepPrinciple, which uses Optimal Transport (OT) methods to generate deterministic transition state structures from reactants and…

Code and data for GEO Defender: Protecting Generative Search from Malicious Generative Engine Optimization.

Staying Visible: Search Optimisation in the Age of Generative Engines

Accelerating Automated Transition State Search with Generative Models in a Low-Data Regime

Open-source Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) platform. Track how ChatGPT, Claude, Perplexity, Gemini, Copilot, Grok, and Google AI Overviews mention and cit…

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) acr…

Open R1 snapshot with Prefix Sliding GRPO recipes

This repository contains experimental reports and training results for my research

[CIKM ’26] Implementation of "Self-Evolving Memory for Generative Recommendation"

Official implementation of GeoSID: Quantizer-Aware Geometric Shaping for Semantic IDs in Generative Recommendation

Differentiable Semantic ID for Generative Recommendation

An automatic refreshing "awesome" paper list for the generative recommendation systems. Updated everyday at 11PM GMT+8, warm and fresh since '26

分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

This compendium reviews significant published research contributions and industrial engineering practices in leveraging Generative AI and LLMs for developing search, recommender, personalization, a…