Zhiwei Deng

Zhiwei Deng is a Research Scientist at Google Deepmind. He was a Postdoc at the Computer Science Department of Princeton University. He earned his PhD at Simon Fraser University in Computer Science.

He is generally interested in building intelligent learning agents with System 1&2. Recently, he is drawn by reparameterizing knowledge in neural networks through Input-Output memories, and building perceptual world model using self-supervised representation learning.

Research

	What is Dataset Distillation Learning? William Yang, Ye Zhu, Zhiwei Deng, Olga Russakovsky ICML 2024
	Perceptual Group Tokenizer: Building Perception with Iterative Grouping Zhiwei Deng, Ting Chen, Yang Li ICLR 2024
	Vision-Language Dataset Distillation Xindi Wu, Byron Zhang, Zhiwei Deng, Olga Russakovsky Arxiv 2023 code / project
	Unseen Image Synthesis with Diffusion Models Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan Arxiv 2023
	Boundary Guided Learning-Free Semantic Control with Diffusion Models Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan Neurips 2023 code / project
	Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks Zhiwei Deng, Olga Russakovsky Neurips 2022 code
	Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky Neurips 2020 code / poster / Princeton Robotics Seminar
	BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps Wang (Bill) Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha ACL 2020 (Oral) code
	Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation Felix Yu, Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky Visual Learning with Limited Labels Workshop, CVPR 2020 (Oral) arxiv / code
	Continuous Graph Flow Zhiwei Deng, Megha Nawhal, Lili Meng, Greg Mori ICML 2020 - Workshop on Graph Representation Learning and Beyond 2020 code / webpage
	Policy Message Passing: Modeling Trajectories for Probabilistic Graph Inference Zhiwei Deng, Xingguo Li, Greg Mori Arxiv 2019
	Talking With Hands 16.2M: A Large-Scale Dataset of Synchronized Body-Finger Motion and Audio for Conversational Motion Analysis and Synthesis. Gilwoo Lee, Zhiwei Deng, Shugao Ma, Takaaki Shiratori, Siddhartha S. Srinivasa, Yaser Sheikh. ICCV 2019 code
	Learning Structured Inference Neural Networks with Label Relations. Nelson Nauata, Hexiang Hu, Guang-tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori PAMI 2019 webpage
	Probabilistic Neural Programmed Networks for Scene Generation. Zhiwei Deng, Jiacheng Chen, Yifang Fu, Greg Mori Neural Information Processing Systems(NeurIPS) 2018 ((Spotlight), 3.5% acceptance rate) code / poster
	Sparsely Aggregated Convolutional Networks. Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori ECCV 2018 code
	Factorized Variational Autoencoders for Modeling Audience Reactions to Movies. Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, Greg Mori CVPR 2017 (Press Coverage CBC News \| PHYS.ORG \| Caltech News)
	Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition. Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori CVPR 2016 arxiv / Webpage / Extended Collective Activity Dataset: train-test split
	A Hierarchical Deep Temporal Model for Group Activity Recognition. Moustafa Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori CVPR 2016 code
	Deep Structured Models For Group Activity Recognition. Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Roshtkhari, Greg Mori BMVC 2015 (oral, acceptance rate=7%)

Invited talks

Princeton University, PIXL talk, 2019.
University of California, Berkeley, EECS, 2019.
Vector Institute's Endless Summer School, 2019.

Service

Senior Program Committee for: IJCAI 2021
Reviewers for: NIPS 2017-2020, CVPR 2017-2020, ICML 2018-2020, ECCV 2018-2020, NIPS 2018-2020, ACL 2020, EMNLP 2020, ICLR 2020, PAMI

Thanks to Jon Barron for this nice website template.