27 citations · 59 across the 9 of their papers we have counts for
9 papers
Improving Policy Optimization with Generalist-Specialist Learning
Zhiwei Jia, Xuanlin Li, Zhan Ling +3
Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically ob…
Learning to Act with Affordance-Aware Multimodal Neural SLAM
Zhiwei Jia, Kaixiang Lin, Yizhou Zhao +3
Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its envi…
LUMINOUS: Indoor Scene Generation for Embodied AI Challenges
Yizhou Zhao, Kaixiang Lin, Zhiwei Jia +4
Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. Howe…
ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations
Tongzhou Mu, Zhan Ling, Fanbo Xiang +6
Object manipulation from 3D visual inputs poses many challenges on building generalizable perception and policy models. However, 3D assets in existing benchmarks mostly lack the di…
Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics
Zhiwei Jia, Bodi Yuan, Kangkang Wang +4
Many applications of unpaired image-to-image translation require the input contents to be preserved semantically during translations. Unaware of the inherently unmatched semantics…
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Tongzhou Mu, Jiayuan Gu, Zhiwei Jia +2
We study how to learn a policy with compositional generalizability. We propose a two-stage framework, which refactorizes a high-reward teacher policy into a generalizable student p…
One-pixel Signature: Characterizing CNN Models for Backdoor Detection
Shanjiaoyang Huang, Weiqi Peng, Zhiwei Jia +1
We tackle the convolution neural networks (CNNs) backdoor detection problem by proposing a new representation called one-pixel signature. Our task is to detect/classify if a CNN mo…
Information-Theoretic Local Minima Characterization and Regularization
Zhiwei Jia, Hao Su
Recent advances in deep learning theory have evoked the study of generalizability across different local minima of deep neural networks (DNNs). While current work focused on either…
Controllable Top-down Feature Transformer
Zhiwei Jia, Haoshen Hong, Siyang Wang +2
We study the intrinsic transformation of feature maps across convolutional network layers with explicit top-down control. To this end, we develop top-down feature transformer (TFT)…