About

Hi! I am Haoran, an MS in Machine Learning student at CMU's Machine Learning Department. Prior to that, I was fortunate to work with Prof. Alan Yuille at Johns Hopkins University and Prof. Huaxiu Yao at UNC-Chapel Hill.

My research lies at the intersection of natural language processing, computer vision, and machine learning, with a particular focus on foundation models (LLMs and VLMs). Currently, I am working on long context foundation models. More broadly, my research involves retrieval-augmented generation, preference optimization, and applications in broader science (e.g., healthcare and ecology).

I am looking for summer research for 2026 and PhD positions starting in Fall 2027. Please reach out if you think my background could be a good fit (haoranl4@cs.cmu.edu).

News

Excited to start my MS in Machine Learning at CMU!
Our work is covered by JIQIZHIXIN (机器之心)! It provides the first theoretical analysis on multimodal RoPEs in long context scenarios. Check it out!
MMed-RAG was accepted by ICLR 2025!
SemDI and RULE were accepted by EMNLP 2024!
LITE was accepted by COLM 2024!

Publications

Please see the full list in Google Scholar.

2025

HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models
Haoran Li, Yingjie Qin, Baoyuan Ou, Lai Xu, Ruiwen Xuo
arXiv Preprint, 2025.

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
Peng Xia, Kangyu Zhu, Haoran Li, Tianze Wang, Weijia Shi, Sheng Wang, Linjun Zhang, James Zou, Huaxiu Yao
International Conference on Learning Representations (ICLR), 2025.

2024

Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network
Haoran Li, Qiang Gao, Hongmei Wu, Li Huang
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.

RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models
Peng Xia*, Kangyu Zhu*, Haoran Liu, Hongtu Zhu, Yun Li, Gang Li, Linjun Zhang, Huaxiu Yao
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.

LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models
Haoran Li, Junqi Liu, Zexian Wang, Shiyuan Luo, Xiaowei Jia, Huaxiu Yao
Conference on Language Modeling (COLM), 2024.

Academic Services

Conference Reviewer: ACL 2025, EMNLP 2025
Conference Workshop Reviewer: ICML 2025 R2-FM

Miscellaneous

I love traveling 🧳, movies 🎥, and basketball 🏀.
I've been to 🇺🇸, 🇶🇦, 🇯🇵, 🇸🇬, 🇭🇰, 🇲🇴, 🇰🇷... Always Exploring!

Top