Hi, I'm Kevin Wang
A
I am an incoming PHD at Univeristy of Texas at Austin and would be advised by Prof.Atlas Wang at VITA group. I enjoy exploring the possibility of combining Vision and AI. At present, my focus is on the innovative fields of Creative Vision and 3D Representation. My passion lies in crafting interactive applications designed to tackle real-world challenges.
Contact me as we could explore the possibilities together!
Publications
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Authors: Kevin Wang*,Zhiwen Fan*, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Venue: NeurIPS (Spotlight)
InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds
Authors: Zhiwen Fan*, Wenyan Cong*, Kairun Wen*, Kevin Wang , Jian Zhang, Xinghao Ding, Danfei Xu, Boris Ivanovic, Marco Pavone, Georgios Pavlakos, Zhangyang Wang, Yue Wang
Venue: Preprint
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
Authors: Wenqing Zheng, S P Sharan, Ajay Jaiswal, Kevin Wang , Yihan Xi, Dejia Xu, Zhangyang Wang
Venue: ICML
Authors: Wenqing Zheng*, S P Sharan*, Zhiwen Fan, Kevin Wang , Yihan Xi, Zhangyang Wang
Venue:PAMI
Experience
- Proposed and implemented an architecture that compressed 3D reconstruction scenes by 15 times compared to the 3D Gaussian model through pruning, distillation, and quantization (400+ stars on github, under CVPR Review)
- Implemented a transformer-based language model that produces syntax error-free python codes, and reaches a state-of-the-art performance with significantly fewer parameters. This work was published at ICML
- Built an innovative algorithm for extracting symbolic representations from visual RL (paper, TPAMI minor） Conceived and implemented the neural guided searching algorithm that is partially differentiable, resulting in increasing scalability of symbolic RL
- Tools: Pytorch, OpenCv
- Enhanced SparkCognition malware detection with dual-layer classification models, using static models for targeted file types and a dynamic model to catch data misclassified by static models.
- Static models: Conducted feature contribution analysis in existing static ML models by pruning noisy features, empirically adding novel features, resulting in runtime reduced by 40%. Leveraged Kubernetes for efficient build and distributive training, reducing training time for static model by 30%.
- Dynamic model: Developed a novel dynamic ML model in Python using LightGBM and translated it to C\# production code, achieving 95\% precision in detecting unseen malware.
- Tools: Python, C#, .Net, Kubernetes
Education
Austin, USA
Degree: Ph.D. candidate in Electrical Computer Engineering advised by Prof. Atlas Wang
Austin, USA
Degree: Bachelor of Science in Computer Science and Bachelor of Science in Mathmatics
GPA: 3.78/4.0
- Computer Vision
- Machine Learning
- Reinforcement Learning
Relevant Courseworks: