J
Jiajun Wu
Researcher at Stanford University
Publications - 216
Citations - 13655
Jiajun Wu is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Object (computer science). The author has an hindex of 48, co-authored 169 publications receiving 9618 citations. Previous affiliations of Jiajun Wu include Massachusetts Institute of Technology & Princeton University.
Papers
More filters
Proceedings ArticleDOI
E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance
TL;DR: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance (E-MAPP) as mentioned in this paper integrates the structural information from a parallel program, promotes the cooperative behaviors grounded in program semantics and improves the time efficiency via a task allocator.
Proceedings ArticleDOI
Physically Plausible Animation of Human Upper Body from a Single Image
TL;DR: In this paper , a reinforcement learning approach is used to generate controllable, dynamically responsive, and photorealistic human animations using an image of a person given an interaction in the image space, such as dragging their hand to various locations.
Posted Content
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control.
TL;DR: In this article, an unsupervised method for shape control through automatically discovered 3D keypoints is proposed. But this method does not address the problem of aligning a source object to a target 3D object from the same object category.
Journal ArticleDOI
TMG: A topology-based motion generalization method with spatial relationship preservation
TL;DR: Li et al. as mentioned in this paper proposed a topology-based motion generalization (TMG) method that abstracts the motion generalisation problem to a mesh deformation optimization, and the spatial relationship between different parts of the robot is captured with a topological-based representation.
Dynamic-Resolution Model Learning for Object Pile Manipulation
TL;DR: In this article , the authors investigate how to learn dynamic and adaptive representations at different levels of abstraction to achieve the optimal trade-off between efficiency and effectiveness in various robotic manipulation tasks.