Huijuan (Noel) Wang
Embedded Files
Biography
I am a Ph.D. student in computer science at the University of Southern California, advised by Prof. Xuezhe Ma. I received my Bachelor's and Master's degrees in computer science from Sun Yat-sen University and worked with Prof. Rong Pan.
My research focuses on generative models and efficient training of large models. I am particularly interested in efficient architectures, multimodal models, and large-scale pretraining.
📪 huijuanw [AT] usc [DOT] edu
Publications
LLM Pretraining
K2-V2: A 360-Open, Reasoning-Enhanced LLM 📃
K2 Team, 2025
Multimodal Generation
Asymmetric Idiosyncrasies in Multimodal Models 📃
Muzi Tao, Chufan Shi, Huijuan Wang, Shengbang Tong, Xuezhe Ma
Arxiv 2026
Graph Representation Learning
Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning 📃
Huijuan Wang, Siming Dai, Weiyue Su, Hui Zhong, Zeyang Fang, Zhengjie Huang, Shikun Feng, Zeyu Chen, Yu Sun, Dianhai Yu
IJCAI 2022
An Adversarial Transfer Network for Knowledge Representation Learning 📃
Huijuan Wang, Shuangyin Li, Rong Pan
TheWebConf 2021
Work Experience
Institute of Foundation Models (IFM)
May. 2025 - Aug. 2025, Mentor: Hector Liu
Topic: Maximal update parameterization (muP)
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Jun. 2024 - Sep. 2024, Mentor: Hector Liu
Topic: Mixture of experts (MOE) model pre-training
Baidu Inc.
Jul. 2021 - Jul. 2023, Mentor: Zeyu Chen
Topic: Graph representation, Efficient fine-tuning
Teaching Assistant
2026 Spring: CSCI544 Applied Natural Language Processing
2025 Fall: CSCI360 Introduction to Artificial Intelligence
2024 Spring: CSCI544 Applied Natural Language Processing
Page updated
Report abuse