Profiles2023-2026
Zhang-Wei Hong
Massachusetts Institute of Technology
6Papers
0Last author
10Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- A Reward-Free Viewpoint on Multi-Objective Reinforcement LearningAuthor 4 of 5ICLR 2026 · 2 citations
- ORSO: Accelerating Reward Design via Online Reward Selection and Policy OptimizationAuthor 3 of 4ICLR 2025
- ReGen: Generative Robot Simulation via Inverse DesignAuthor 3 of 8ICLR 2025
- Curiosity-driven Red-teaming for Large Language ModelsAuthor 1 of 8ICLR 2024 · 84 citations
- Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced DatasetsAuthor 1 of 9NeurIPS 2023 · 34 citations
- Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory WeightingAuthor 1 of 4ICLR 2023 · 1 citation
