Profiles2024-2026
Paul Weng
Duke Kunshan University
7Papers
1Last author
9Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- Generalizable Coarse-to-Fine Robot Manipulation via Language-Aligned 3D KeypointsAuthor 7 of 7ICLR 2026 · 6 citations
- Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement LearningAuthor 3 of 4NeurIPS 2025 · 1 citation
- Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability QueriesAuthor 5 of 6ICML 2025
- Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline DataAuthor 4 of 5AAAI 2025
- Progressive Learning with Human Feedback for Personalized Adaptive Video StreamingAuthor 5 of 6ACM MM 2025
- Reinforcement Learning from Imperfect Corrective Actions and Proxy RewardsAuthor 4 of 9ICLR 2025
- INViT: A Generalizable Routing Problem Solver with Invariant Nested View TransformerAuthor 3 of 4ICML 2024 · 39 citations
