About

Hi! I am Haoran, an MS student at the Machine Learning Department of Carnegie Mellon University. My research focuses on building intelligent agents that can learn from rich contexts and reason over long horizons to execute complex tasks. Toward this goal, my work develops novel architectures for foundation models and reinforcement learning algorithms to improve their reasoning.

Previously, I have been fortunate to work with Prof. Ruslan Salakhutdinov at Sooth Labs, Prof. Alan Yuille at Johns Hopkins University, and Prof. Huaxiu Yao at UNC.

News

DMI was accepted by SIGIR 2026!
HoPE is cited by the Qwen team in developing multimodal RoPE for Qwen3-VL and demonstrates the best performance on video tasks!
HoPE was accepted by NeurIPS 2025!
Excited to start my MS in Machine Learning at CMU!
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.

2026

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
Haoran Li, Sucheng Ren, Alan Yuille, Feng Wang
arXiv preprint, 2026.

Countering Interest Over-Smoothing: Distilling Latent Factors via Diffusion for Multi-Interest Retrieval
Yankun Le*, Haoran Li*, Baoyuan Ou, Yingjie Qin, Zhixuan Yang, Ruilong Su, Fu Zhang
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2026.

2025

HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
Haoran Li, Yingjie Qin, Baoyuan Ou, Lai Xu, Ruiwen Xu
Advances in Neural Information Processing Systems (NeurIPS), 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 Li, 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:

Advances in Neural Information Processing Systems (NeurIPS): 2026
International Conference on Learning Representations (ICLR): 2026
Annual Meeting of the Association for Computational Linguistics (ACL): 2025, 2026
Conference on Empirical Methods in Natural Language Processing (EMNLP): 2025

Journal Reviewer:

Neural Networks

Miscellaneous

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