Mufei Li (李牧非)'s Homepage

I’m a third-year PhD student in machine learning at Georgia Institute of Technology, advised by Prof. Pan Li. My current research interest is memory mechanisms of foundation models, e.g., retrieval-augmented generation, long-context reasoning, long-term memory, etc.

Prior to that, I was a software development engineer (SDE) at Amazon Web Services (AWS) Shanghai AI Lab. I received my bachelor’s degree in Honors Math from NYU Shanghai.

News

Sep 27, 2025	Check EAPrivacy, a benchmark to quantify the physical-world privacy awareness of LLMs. This work was led by Xinjie, who’s looking for internship opportunities in summer 2026.
Sep 21, 2025	HaystackCraft, our new benchmark on LLM long-context and agentic reasoning, has been accepted by NeurIPS 2025 workshop on Evaluating the Evolving LLM Lifecycle. Congratulations to all the co-authors!
Sep 18, 2025	Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models has been accepted by NeurIPS 2025! Congratulations to Haoyu and all the co-authors!
Jun 12, 2025	Check our new paper on better leveraging the LLM KV cache for modeling multi-doc interdependencies, Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models, led by Haoyu!
May 27, 2025	I’m starting a new position as Research Scientist Intern at Meta Ranking and Foundational AI! I’m based in Sunnyvale, California.

Selected Publications

arXiv

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

Mufei Li, Dongqi Fu, Limei Wang, Si Zhang, Hanqing Zeng, Kaan Sancak, Ruizhong Qiu, Haoyu Wang, Xiaoxin He, Xavier Bresson, Yinglong Xia, Chonglin Sun, and Pan Li

arXiv preprint arXiv:2510.07414, 2025

arXiv Bib Code

@article{li2025haystack,
  title = {Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation},
  author = {Li, Mufei and Fu, Dongqi and Wang, Limei and Zhang, Si and Zeng, Hanqing and Sancak, Kaan and Qiu, Ruizhong and Wang, Haoyu and He, Xiaoxin and Bresson, Xavier and Xia, Yinglong and Sun, Chonglin and Li, Pan},
  journal = {arXiv preprint arXiv:2510.07414},
  year = {2025},
}

ICLR
Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Mufei Li, Siqi Miao, and Pan Li

In International Conference on Learning Representations, 2025

Mufei Li and Siqi Miao contributed equally to this work. This work was selected for oral presentation at [ICLR 2025 workshop on Foundation Models in the Wild](https://fm-wild-community.github.io/)

arXiv Bib Code ...⭐
@inproceedings{li2025subgraphrag, title = {Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation}, author = {Li, Mufei and Miao, Siqi and Li, Pan}, booktitle = {International Conference on Learning Representations}, year = {2025}, github_stars = {Graph-COM/SubgraphRAG}, }

ICLR Spotlight

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

Mufei Li, Viraj Shitole, Eli Chien, Changhai Man, Zhaodong Wang, Srinivas Sridharan, Ying Zhang, Tushar Krishna, and Pan Li

In International Conference on Learning Representations, 2025

Selected for spotlight presentation at the ICLR 2025 workshop ["Will Synthetic Data Finally Solve the Data Access Problem?"](https://synthetic-data-iclr.github.io/)

arXiv Bib Code ...⭐

@inproceedings{li2024layerdag,
  title = {Layer{DAG}: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation},
  author = {Li, Mufei and Shitole, Viraj and Chien, Eli and Man, Changhai and Wang, Zhaodong and Sridharan, Srinivas and Zhang, Ying and Krishna, Tushar and Li, Pan},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
  note = {Selected for spotlight presentation at the ICLR 2025 workshop ["Will Synthetic Data Finally Solve the Data Access Problem?"](https://synthetic-data-iclr.github.io/)},
  github_stars = {Graph-COM/LayerDAG},
}

TMLR

GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?

Mufei Li, Eleonora Kreačić, Vamsi K. Potluru, and Pan Li

Transactions on Machine Learning Research, 2024

arXiv Bib Code ...⭐

@article{li2024graphmaker,
  title = {GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?},
  author = {Li, Mufei and Kreačić, Eleonora and Potluru, Vamsi K. and Li, Pan},
  year = {2024},
  journal = {Transactions on Machine Learning Research},
  github_stars = {Graph-COM/GraphMaker},
}