Scholar
Kaixin Wang
Google Scholar ID: AP_Yd6wAAAAJ
Microsoft Research
Citations & Impact
Citations
2,309
H-index
10
i10-index
10
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Published 'Dyn-O: Building Structured World Models with Object-Centric Representations' at NeurIPS 2025.
- Published 'Improving Token-Based World Models with Parallel Observation Prediction' at ICML 2024.
- Published 'Reachability-Aware Laplacian Representation in Reinforcement Learning' at ICML 2023.
- Published 'The Geometry of Robust Value Functions' at ICML 2022.
- Published 'Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing' at ICML 2021.
- Served as reviewer and area chair for top conferences and journals including AAAI (2023–2025), ICLR (2020–2025), ICML (2020–2025), NeurIPS (2020–2024), etc.
- Submitted to MineRL competition 2019.
- Curated a list of papers on generalization in (deep) reinforcement learning.