Yujie Lu

Yujie Lu (卢雨洁) is an AI Research Scientist at Meta Superintelligence Labs, a core contributor to Muse Wonder and Muse Spark, focusing on pretraining science, scaling, data, and evaluation. Previously, she was a core contributor to the Llama model series, working on post-training. She earned her Ph.D. from UC Santa Barbara and her bachelor's degree from Chu Kochen Honors College, Zhejiang University.

Email: yujielu10@gmail.com

Email / Google Scholar / Github / LinkedIn / X
Yujie Lu

News

News! 08/05/2026 Muse Spark, Muse Wonder and Muse Code Blog

News! 12/18/2025 Excited about the launch of our Native Video-to-Video Generation Model!

News! 09/20/2025 MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research is accepted at NeurIPS 2025 D&B Track!

News! 04/05/2025 Checkout out our first The llama 4 herd: The beginning of a new era of natively multimodal ai innovation!

News! 02/26/2025 VITED: Video Temporal Evidence Distillation is accepted at CVPR 2025!

News! 01/24/2025 I successfully complete my PhD defense and will join Meta GenAI Llama Research Team!

Selected Publications

VITED: Video Temporal Evidence Distillation

Yujie Lu, Yale Song, William Yang Wang, Lorenzo Torresani, Tushar Nagarajan

Conference on Computer Vision and Pattern Recognition (CVPR), 2025

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

Yujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, Bill Yuchen Lin

Conference on Neural Information Processing Systems (NeurIPS), Dataset and Benchmark, 2024

Multimodal Procedural Planning via Dual Text-Image Prompting

Yujie Lu, Pan Lu, Zhiyu Chen, Wanrong Zhu, Xin Eric Wang, William Yang Wang

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

From Text to Pixel: Advancing Long-Context Understanding in MLLMs

Yujie Lu, Xiujun Li, Tsu-Jui Fu, Miguel Eckstein, William Yang Wang

ICML 2024 Workshop LCFM, 2024

Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?

Yujie Lu*, Xiujun Li*, Zhe Gan, Jianfeng Gao, William Yang Wang, Yejin Choi

NeurIPS Workshop on Adaptive Foundation Models, 2024

Visual grounding for user interfaces

Yijun Qian, Yujie Lu, Alexander G Hauptmann, Oriana Riva

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024

Imagenhub: Standardizing the evaluation of conditional image generation models

Max Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, Wenhu Chen

International Conference on Learning Representations (ICLR), 2024

Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought

Vaishnavi Himakunthala, Andy Ouyang, Daniel Philip Rose, Ryan He, Alex Mei, Yujie Lu, Chinmay Sonar, Michael Saxon, William Yang Wang

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

Yujie Lu, Xianjun Yang, Xiujun Li, Xin Eric Wang, William Yang Wang

Conference on Neural Information Processing Systems (NeurIPS), 2023

Neuro-Symbolic Causal Procedural Planning with Commonsense Prompting

Yujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, William Yang Wang

International Conference on Learning Representations (ICLR), Spotlight, 2023

ULN: Towards Underspecified Vision-and-Language Navigation

Weixi Feng, Tsu-Jui Fu, Yujie Lu, William Yang Wang

The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022

Imagination-Augmented Natural Language Understanding

Yujie Lu, Wanrong Zhu, Xin Eric Wang, Miguel Eckstein, William Yang Wang,

North American Chapter of the Association for Computational Linguistics (NAACL), Oral Presentation, 2022