generative-recommendation

Minimal reproduction of OneRec

A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.

《推荐系统：工业架构与核心算法》开源书稿

[Pytorch] Unofficial Implementation of "Recommender Systems with Generative Retrieval"

[KDD2026] The repo contains the code for "FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets"

Updating curated list of research advancements on item identification and item tokenization in generative recommender systems. The survey is titled "A Survey of Item Identifiers in Generative Recommendation: Construction, Alignment, and Generation"

Generative model for sequential recommendation based on Convolution Neural Networks (CNN))

Differentiable Semantic ID for Generative Recommendation

Code for Multi-Aspect Cross-modal Quantization for Generative Recommendation. (AAAI 2026 Oral)

WWW 2025 | FuXi-alpha: feature-interaction enhanced Transformer for scalable generative recommendation.

The implementations of paper "Reinforced Preference Optimization for Recommendation" (ReRe).

An extremely modular, easy-to-use, and research-oriented framework for Generative Recommendation.

arXiv 2025 | FuXi-beta: lightweight and fast generative recommendation.

Implementation of "Bringing Reasoning to LLM-based Generative Recommendation Through the Lens of Cascaded Ranking" (WWW'26)

[Pytorch] Official Implementation of "RoTE: Coarse-to-Fine Multi-Level Rotary Time Embedding for Sequential Recommendation" (SIGIR'26)

📚 每日精选推荐算法论文解读 | 推荐系统 · 计算广告 · 搜索 | 配套微信公众号「稳扎稳打学AI」

Evidence-first OneRec reproduction: controlled SFT, Semantic ID ablations, statistical audits, and interactive visualization.

Auditable end-to-end reproduction of the 2025 Tencent Ads generative recommendation baseline on TencentGR-1M.

Public RFP and executable reference architecture for a production Feed, search, and recommendation platform

An AI coding agent that lives in your terminal, reading codebases, editing files, and routing requests across multiple LLM providers with cost-aware failover.