Jiale Fu
Master's student at Southeast University and PALM Lab
Nanjing, China
I am Jiale Fu, a Master’s student at Southeast University’s PALM Lab, advised by Prof. Xu Yang. My research focuses on improving the efficiency of Large Language Models. Currently, I work at EAGLE CROP, where I am responsible for EAGLE-4 architecture design, algorithm development, and training system.
Before graduate study, I completed a bachelor’s degree in mathematics at Southeast University, where I was advised by Prof. Wenwu Yu and worked on complex networks.
Research Interests
My research interests focus on LLM efficiency, particularly:
- speculative decoding
- sparse attention
- co-design of algorithms and inference infrastructure
Experience
- Southeast University - Master’s Student, Sept 2024-Present. Conducting research in the School of Computer Science and Engineering and PALM Lab.
- EAGLE CROP - Research Intern, Aug 2025-Present. Working on EAGLE-4, responsible for architecture design, algorithm development, and training system. Mentored by Hongyang Zhang.
- Shopee R&D Center - Multimodal AI Intern, Jun 2024-Sept 2024. Worked on multimodal tokenization for large multimodal model pretraining.
- Baidu Research - Research Intern, Nov 2023-May 2024. Mentored by Yaqing Wang and focused on reasoning and in-context learning for large language models.
- Southeast University - Bachelor’s Student in Mathematics, Sept 2020-Jun 2024.
News
| May 01, 2026 | ICML 2026 Spotlight Rethinking LLM Ensembling from the Perspective of Mixture Models was accepted to ICML 2026 as a Spotlight presentation. |
|---|---|
| Jan 25, 2026 | |
| Nov 03, 2025 | GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning was accepted to AAAI 2026. |
| May 01, 2025 | Fast Large Language Model Collaborative Decoding via Speculation was accepted to ICML 2025. |
| Feb 26, 2025 | Mimic In-Context Learning for Multimodal Tasks was accepted to CVPR 2025. |
