Weiyao Wang

Logo

Ph.D. student @ Hopkins

View the Project on GitHub Wangweiyao/about-me

Bio

I am a 4th year Ph.D. student in the Computer Science department at the Johns Hopkins University in Baltimore, Maryland. I work with Prof. Gregory Hager on vision-based robotics manipulation. My research topics include: 1) Visual representation for robot manipulation. 2) Domain adaptation (e.g., sim-to-real) for visual policies. 3) Language-conditioned robot manipulation. During Ph.D., I also worked with BAIDU Robotics and Autonomous Driving Lab (RAL) and AKASA Inc. as summer research intern.

I completed my undergraduate program at the Duke University in Durham, North Carolina with double major in Computer Science & Statistics and worked with Prof. Lawrence Carin in deep generative models. During undergrad, I also did a software enginnering internship at Facebook and a research internship at UC Berkeley with Prof. Dawn Song and Prof. Bo Li.

Papers in computer vision, reinforcement learning and robotics

  1. VIHE: Transformer-Based 3D Object Manipulation Using Virtual In-Hand View Weiyao Wang , Yutian Lei, Shiyu Jin, Gregory D. Hager and Liangjun Zhang. IROS 2024. [Project Site] [Paper][Code]

  2. Adapting Visual Policies via Predicted Rewards Weiyao Wang , Xinyuan Zhang and Gregory D. Hager. L4DC 2024.

  3. PromptAdapt: Domain Adaptation of Visual Policies with a Single Demonstration Weiyao Wang and Gregory D. Hager. ICRA 2024.

  4. RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild Weiyao Wang, Byung-Hak Kim and Varun Ganapathi. Oral presentation in Table Representation Learning Workshop, NeurIPS 2023. [Paper] [Talk]

  5. Dynamical Scene Representation and Control with Keypoint-Conditioned Neural Radiance Field Weiyao Wang, Andrew S. Morgan, Aaron M. Dollar, Gregory D. Hager CASE 2022. [Paper]

  6. Learn Proportional Derivative Controllable Latent Space from Pixels Weiyao Wang , Marin Kobilarov, and Gregory D. Hager. CASE 2022. [Paper]

  7. How You Act Tells a Lot: Privacy-Leaking Attack on Deep Reinforcement Learning Xinlei Pan, _Weiyao Wang_ , Xiaoshuai Zhang*, Bo Li, Jinfeng Yi, and Dawn Song. Appearing in AAMAS, 2019. [Paper]

Papers in deep generative models

  1. JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets Yunchen Pu, Shuyang Dai, Zhe Gan, Weiyao Wang, Guoyin Wang, Yizhe Zhang, Ricardo Henao, Lawrence Carin. Appearing in ICML, 2018. [Paper]

  2. Adversarial symmetric variational autoencoder Yuchen Pu, Weiyao Wang, Ricardo Henao, Liqun Chen, Zhe Gan, Chunyuan Li, Lawrence Carin. Appearing in NeuralPS, 2017. [Paper]

  3. Triangle generative adversarial networks Zhe Gan, Liqun Chen, Weiyao Wang, Yuchen Pu, Yizhe Zhang, Lawrence Carin. Appearing in NeuralPS, 2017. [Paper]

Image