awesome-LLM-resources and Awesome-LLM-Long-Context-Modeling
These two tools are complements because Xnhyacinth/Awesome-LLM-Long-Context-Modeling provides a focused collection of resources specifically for long context modeling in LLMs, which is a specialized sub-topic within the broader comprehensive set of LLM resources offered by WangRongsheng/awesome-LLM-resources.
About awesome-LLM-resources
WangRongsheng/awesome-LLM-resources
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
Curated collection of 25+ categorized resource sections covering the complete LLM development lifecycle, from data processing tools (MinerU, Docling) and synthetic data generation frameworks (Distilabel, llm-swarm) to specialized domains like agentic systems, multimodal models, and reasoning approaches (o1/o3 variants). Organized as a living documentation repository with continuous updates linking to papers, tutorials, courses, and community resources, enabling developers to navigate fragmented LLM research and tooling across training, inference optimization, evaluation benchmarks, and emerging protocols like MCP.
About Awesome-LLM-Long-Context-Modeling
Xnhyacinth/Awesome-LLM-Long-Context-Modeling
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
Organizes research across 16+ technical categories including efficient attention mechanisms (sparse, linear, hierarchical), state space models, retrieval-augmented generation, and compression techniques for long-context processing. Maintains curated listings of papers on length extrapolation, KV cache optimization, long-horizon video understanding, and chain-of-thought reasoning, with weekly updates tracking emerging work. Includes links to a formal comprehensive survey paper and companion research repository for deeper exploration of architectural innovations and benchmark evaluations.
Scores updated daily from GitHub, PyPI, and npm data. How scores work