Sotabase

Career

· MPH, Dartmouth College2020–
· Doctor of Philosophy - PhD, Computer Science, University of California, Berkeley2020–
· PhD Student, University of California, Berkeley2020–
· Research Assistant, University of California, Berkeley2020–
· Graduate Student, University of Toronto2015–2020
· Undergraduate Studies, University of Toronto2015–2020

Publications (21)

Offline Reinforcement Learning as One Big Sequence Modeling Problem
Neural Information Processing Systems · 2021
801
cited
OpenEQA: Embodied Question Answering in the Era of Foundation Models
Computer Vision and Pattern Recognition · 2024
230
cited
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
Neural Information Processing Systems · 2019
121
cited
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
International Conference on Learning Representations · 2018
107
cited
Learning Visuotactile Skills With Two Multifingered Hands
IEEE International Conference on Robotics and Automation · 2024
102
cited
Reinforcement Learning as One Big Sequence Modeling Problem
arXiv.org · 2021
90
cited
Flow Q-Learning
International Conference on Machine Learning · 2025
60
cited
Efficient Deep Reinforcement Learning Requires Regulating Overfitting
International Conference on Learning Representations · 2023
43
cited
RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
arXiv.org · 2024
30
cited
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
International Conference on Learning Representations · 2024
28
cited
Reinforcement Learning with Action Chunking
arXiv.org · 2025
27
cited
Accelerating Exploration with Unlabeled Prior Data
Neural Information Processing Systems · 2023
18
cited
Understanding the Complexity Gains of Single-Task RL with a Curriculum
International Conference on Machine Learning · 2022
18
cited
EXPO: Stable Reinforcement Learning with Expressive Policies
arXiv.org · 2025
7
cited
Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
International Conference on Machine Learning · 2024
7
cited
AdaCat: Adaptive Categorical Discretization for Autoregressive Models
Conference on Uncertainty in Artificial Intelligence · 2022
4
cited
Q-learning with Adjoint Matching
2026
1
cited
Decoupled Q-Chunking
arXiv.org · 2025
U NDERSTANDING THE C OMPLEXITY
2022
Sotabase
Qiyang Li | Researcher Profile | Sotabase | Sotabase