Statistical Learning & AI Group
Department of Computer Science
The University of Texas at Austin
Email: lmwu at cs dot utexas dot edu
I am a fifth-year computer science Ph.D. student at the University of Texas at Austin, advised by Professor Qiang Liu. My research interests are building the efficiency model and developing the generative model for vision and 3D tasks.
Research Intern
Meta Reality Lab, 05/2022 - 09/2022
Develop an efficient and easy-to-use feature fusion method for the 3D detection task.
Design fast 3D point cloud generation model with comparable performance compared with diffusion based method
Research Intern
Microsoft Cloud AI, 05/2021 - 09/2021
Efficient, plug-in & play Mixture-of-expert model for vision transformer.
Research Intern
ByteDance AML, 05/2020 - 08/2020
Neural architecture search method for sparse feature selection for Douyin CVR and CTR model.
Fast Point Cloud Generation with Straight Flows
Lemeng Wu, Dilin Wang, Chengyue Gong, Xingchao Liu, Yunyang Xiong, Rakesh Ranjan, Raghuraman Krishnamoorthi, Vikas Chandra, Qiang Liu
Computer Vision and Pattern Recognition (CVPR) 2023
[paper]
FlowGrad: Controlling the Output of Generative ODEs with Gradients
Xingchao Liu, Lemeng Wu, Shujian Zhang, Chengyue Gong, Wei Ping, Qiang Liu
Computer Vision and Pattern Recognition (CVPR) 2023
PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra
Arxiv Preprint
[paper]
Learning Diffusion Bridges on Constrained Domains
Xingchao Liu, Lemeng Wu, Mao Ye, Qiang Liu
International Conference on Learning Representations (ICLR) 2023
[paper]
Neural Volumetric Mesh Generator
Yan Zheng*, Lemeng Wu*, Xingchao Liu, Zhen Chen, Qiang Liu, Qixing Huang
NeurIPS 2022 Workshop on Score-Based Methods
[paper]
Diffusion-based Molecule Generation with Informative Prior Bridges
Lemeng Wu*, Chengyue Gong*, Qiang Liu
Neural Information Processing Systems (NeurIPS) 2022
[paper]
First Hitting Diffusion Models
Mao Ye, Lemeng Wu, Qiang Liu
Neural Information Processing Systems (NeurIPS) 2022
[paper]
How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity
Chengyue Gong*, Lemeng Wu*, Qiang Liu
Proceedings of the 39th International Conference on Machine Learning (ICML) 2022
[paper]
Residual Mixture of Experts
Lemeng Wu, Mengchen Liu, Yinpeng Chen, Dongdong Chen, Xiyang Dai, Yuan Lu
Arxiv Preprint
[paper]
Fusedream: Training-free text-to-image generation with improved clip+ gan space optimization
Xingchao Liu, Chengyue Gong, Lemeng Wu, Shujian Zhang, Hao Su, Qiang Liu
Arxiv Preprint
Centroid transformers: Learning to abstract with attention
Lemeng Wu, Xingchao Liu, Qiang Liu
Arxiv Preprint
[paper]
Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks
Lemeng Wu*, Bo Liu*, Peter Stone and Qiang Liu
Neural Information Processing Systems (NeurIPS) 2020
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Mao Ye*, Lemeng Wu* and Qiang Liu
Neural Information Processing Systems (NeurIPS) 2020
Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
Dilin Wang*, Meng Li*, Lemeng Wu, Vikas Chandra and Qiang Liu
NeurIPS 2019 Workshop on Energy Efficient Machine Learning and Cognitive Computing
Splitting Steepest Descent for Progressive Training of Neural Networks
Qiang Liu, Lemeng Wu* and Dilin Wang*
Neural Information Processing Systems (NeurIPS) 2019 Spotlight
Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou and Qixing Huang.
Computer Vision and Pattern Recognition (CVPR) 2019. Oral Presentation
[paper]
Generating Animated Videos of Human Activities from Natural Language Descriptions
Lemeng Wu*, Angela S. Lin*, Rodolfo Corona, Kevin Tai, Qixing Huang, and Raymond J. Mooney
Visually Grounded Interaction and Language Workshop at NeurIPS, 2018
2022 Google Workshop on Sparsity and Adaptive Computation: Residual Mixture of Experts [link]
Teaching Assistant: UT CS395T Physical Simulation , 2019 Spring
Teaching Assistant: UT CS303E Elements of Computers and Programming , 2018 Fall