Ji Hou
RESEARCH SCIENTIST | MENLO PARK, UNITED STATES
I am a Research Scientist at Meta Generative AI. Previously, I did my Ph.D. at TUM Visual Computing Group headed by Prof. Matthias Niessner, where I work on Computer Vision and 3D Scene Understanding. During my Ph.D., I did an internship at Facebook AI Research (FAIR) with Saining Xie and Benjamin Graham on 3D representation and data-efficient learning.
Research Areas
Ji's Publications
January 02, 2026
COMPUTER VISION
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
Kunpeng Li, Jialiang Wang, Weifeng Chen, Xiaoliang Dai, Xuan Ju, Alan Yuille, Ali Thabet, Chu Wang, Felix Xu, Feng Liang, Ji Hou, Junzhe Sun, Menglin Jia, Yuanhao Cai
January 02, 2026
June 05, 2024
COMPUTER VISION
Cache Me if You Can: Accelerating Diffusion Models through Block Caching
Christian Rupprecht, Daniel Cramers, Jialiang Wang, Artsiom Sanakoyeu, Bichen Wu, Edgar Schoenfeld, Felix Wimbauer, Ji Hou, Jonas Kohler, Peizhao Zhang, Peter Vajda, Sam Tsai, Zijian He
June 05, 2024
September 27, 2023
COMPUTER VISION
Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
Ji Hou, Abhimanyu Dubey, Abhishek Kadian, Devi Parikh, Dhruv Mahajan, Filip Radenovic, Jialiang Wang, Kevin Chih-Yao Ma, Kunpeng Li, Matthew Yu, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Roshan Sumbaly, Rui Wang, Sam Tsai, Simon Vandenhende, Simran Motwani, Vignesh Ramanathan, Vladan Petrovic, Xiaofang Wang, Xiaoliang Dai, Yi Wen, Yiwen Song, Yue (R) Zhao, Zijian He
September 27, 2023
Our approach
Latest news
Foundational models
Meta © 2026