Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Ying Nian Wu

Ying Nian Wu

Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification


Aug 26, 2021
Bo Pang, Ying Nian Wu

Figure 1 for Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification
Figure 2 for Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification
Figure 3 for Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification
Figure 4 for Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification
* 8 pages 
  Access Paper or Ask Questions

Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI


Jul 26, 2021
Quanshi Zhang, Tian Han, Lixin Fan, Zhanxing Zhu, Hang Su, Ying Nian Wu, Jie Ren, Hao Zhang


  Access Paper or Ask Questions

SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues


Jun 24, 2021
Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu

Figure 1 for SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
Figure 2 for SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
Figure 3 for SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
Figure 4 for SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
* Long paper (oral) accepted by ACL-IJCNLP 2021 
  Access Paper or Ask Questions

Planning on a (Risk) Budget: Safe Non-Conservative Planning in Probabilistic Dynamic Environments


Jun 16, 2021
Hung-Jui Huang, Kai-Chi Huang, Michal Čáp, Yibiao Zhao, Ying Nian Wu, Chris L. Baker

Figure 1 for Planning on a (Risk) Budget: Safe Non-Conservative Planning in Probabilistic Dynamic Environments
Figure 2 for Planning on a (Risk) Budget: Safe Non-Conservative Planning in Probabilistic Dynamic Environments
Figure 3 for Planning on a (Risk) Budget: Safe Non-Conservative Planning in Probabilistic Dynamic Environments
Figure 4 for Planning on a (Risk) Budget: Safe Non-Conservative Planning in Probabilistic Dynamic Environments
* 9 pages, 5 figures, International Conference on Robotics and Automation 2021 
  Access Paper or Ask Questions

SAS: Self-Augmented Strategy for Language Model Pre-training


Jun 14, 2021
Yifei Xu, Jingqiao Zhang, Ru He, Liangzhu Ge, Chao Yang, Cheng Yang, Ying Nian Wu

Figure 1 for SAS: Self-Augmented Strategy for Language Model Pre-training
Figure 2 for SAS: Self-Augmented Strategy for Language Model Pre-training
Figure 3 for SAS: Self-Augmented Strategy for Language Model Pre-training
Figure 4 for SAS: Self-Augmented Strategy for Language Model Pre-training
* 13 pages, 3 figures 
  Access Paper or Ask Questions

Generative Text Modeling through Short Run Inference


Jun 08, 2021
Bo Pang, Erik Nijkamp, Tian Han, Ying Nian Wu

Figure 1 for Generative Text Modeling through Short Run Inference
Figure 2 for Generative Text Modeling through Short Run Inference
Figure 3 for Generative Text Modeling through Short Run Inference
Figure 4 for Generative Text Modeling through Short Run Inference
* 10 pages 
  Access Paper or Ask Questions

Trajectory Prediction with Latent Belief Energy-Based Model


Apr 07, 2021
Bo Pang, Tianyang Zhao, Xu Xie, Ying Nian Wu

Figure 1 for Trajectory Prediction with Latent Belief Energy-Based Model
Figure 2 for Trajectory Prediction with Latent Belief Energy-Based Model
Figure 3 for Trajectory Prediction with Latent Belief Energy-Based Model
Figure 4 for Trajectory Prediction with Latent Belief Energy-Based Model
* 13 pages 
  Access Paper or Ask Questions

Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance


Mar 26, 2021
Xu Xie, Chi Zhang, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

Figure 1 for Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
Figure 2 for Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
Figure 3 for Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
Figure 4 for Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
* ICRA 2021 paper. Project: https://xuxie1031.github.io/projects/GTA/GTAProj.html 
  Access Paper or Ask Questions

Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation


Mar 07, 2021
Jianwen Xie, Zilong Zheng, Xiaolin Fang, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
Figure 2 for Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
Figure 3 for Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
Figure 4 for Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
* The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI) 2021 
  Access Paper or Ask Questions

A HINT from Arithmetic: On Systematic Generalization of Perception, Syntax, and Semantics


Mar 02, 2021
Qing Li, Siyuan Huang, Yining Hong, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

Figure 1 for A HINT from Arithmetic: On Systematic Generalization of Perception, Syntax, and Semantics
Figure 2 for A HINT from Arithmetic: On Systematic Generalization of Perception, Syntax, and Semantics
Figure 3 for A HINT from Arithmetic: On Systematic Generalization of Perception, Syntax, and Semantics
Figure 4 for A HINT from Arithmetic: On Systematic Generalization of Perception, Syntax, and Semantics
* Preliminary work 
  Access Paper or Ask Questions

HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving


Feb 22, 2021
Sirui Xie, Xiaojian Ma, Peiyu Yu, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

Figure 1 for HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving
Figure 2 for HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving
Figure 3 for HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving

  Access Paper or Ask Questions

Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis


Dec 25, 2020
Jianwen Xie, Zilong Zheng, Ruiqi Gao, Wenguan Wang, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis
Figure 2 for Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis
Figure 3 for Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis
Figure 4 for Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis
* 16 pages. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2020. arXiv admin note: substantial text overlap with arXiv:1804.00586 
  Access Paper or Ask Questions

Learning Energy-Based Models by Diffusion Recovery Likelihood


Dec 15, 2020
Ruiqi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P. Kingma

Figure 1 for Learning Energy-Based Models by Diffusion Recovery Likelihood
Figure 2 for Learning Energy-Based Models by Diffusion Recovery Likelihood
Figure 3 for Learning Energy-Based Models by Diffusion Recovery Likelihood
Figure 4 for Learning Energy-Based Models by Diffusion Recovery Likelihood

  Access Paper or Ask Questions

Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling


Oct 19, 2020
Bo Pang, Erik Nijkamp, Jiali Cui, Tian Han, Ying Nian Wu

Figure 1 for Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
Figure 2 for Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
Figure 3 for Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
Figure 4 for Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
* work in progress 
  Access Paper or Ask Questions

Learning Latent Space Energy-Based Prior Model for Molecule Generation


Oct 19, 2020
Bo Pang, Tian Han, Ying Nian Wu

Figure 1 for Learning Latent Space Energy-Based Prior Model for Molecule Generation
Figure 2 for Learning Latent Space Energy-Based Prior Model for Molecule Generation

  Access Paper or Ask Questions

A Representational Model of Grid Cells Based on Matrix Lie Algebras


Jun 18, 2020
Ruiqi Gao, Jianwen Xie, Song-Chun Zhu, Ying Nian Wu

Figure 1 for A Representational Model of Grid Cells Based on Matrix Lie Algebras
Figure 2 for A Representational Model of Grid Cells Based on Matrix Lie Algebras
Figure 3 for A Representational Model of Grid Cells Based on Matrix Lie Algebras
Figure 4 for A Representational Model of Grid Cells Based on Matrix Lie Algebras

  Access Paper or Ask Questions

Learning Latent Space Energy-Based Prior Model


Jun 15, 2020
Bo Pang, Tian Han, Erik Nijkamp, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Learning Latent Space Energy-Based Prior Model
Figure 2 for Learning Latent Space Energy-Based Prior Model
Figure 3 for Learning Latent Space Energy-Based Prior Model
Figure 4 for Learning Latent Space Energy-Based Prior Model
* 22 pages, 4 figures 
  Access Paper or Ask Questions

Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC


Jun 12, 2020
Erik Nijkamp, Ruiqi Gao, Pavel Sountsov, Srinivas Vasudevan, Bo Pang, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Figure 2 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Figure 3 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC
Figure 4 for Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC

  Access Paper or Ask Questions

Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning


Jun 11, 2020
Qing Li, Siyuan Huang, Yining Hong, Yixin Chen, Ying Nian Wu, Song-Chun Zhu

Figure 1 for Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
Figure 2 for Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
Figure 3 for Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
Figure 4 for Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
* ICML 2020. Project page: https://liqing-ustc.github.io/NGS 
  Access Paper or Ask Questions

Joint Training of Variational Auto-Encoder and Latent Energy-Based Model


Jun 10, 2020
Tian Han, Erik Nijkamp, Linqi Zhou, Bo Pang, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
Figure 2 for Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
Figure 3 for Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
Figure 4 for Joint Training of Variational Auto-Encoder and Latent Energy-Based Model

  Access Paper or Ask Questions

Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense


Apr 20, 2020
Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu, Joshua B. Tenenbaum, Song-Chun Zhu

Figure 1 for Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
Figure 2 for Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
Figure 3 for Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
Figure 4 for Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
* Engineering, Feb, 2020 
 * For high quality figures, please refer to http://wellyzhang.github.io/attach/dark.pdf 
  Access Paper or Ask Questions

Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification


Apr 02, 2020
Jianwen Xie, Yifei Xu, Zilong Zheng, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
Figure 2 for Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
Figure 3 for Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
Figure 4 for Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification

  Access Paper or Ask Questions

Learning Deep Generative Models with Short Run Inference Dynamics


Dec 14, 2019
Erik Nijkamp, Bo Pang, Tian Han, Linqi Zhou, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Learning Deep Generative Models with Short Run Inference Dynamics
Figure 2 for Learning Deep Generative Models with Short Run Inference Dynamics
Figure 3 for Learning Deep Generative Models with Short Run Inference Dynamics
Figure 4 for Learning Deep Generative Models with Short Run Inference Dynamics

  Access Paper or Ask Questions

Flow Contrastive Estimation of Energy-Based Models


Dec 02, 2019
Ruiqi Gao, Erik Nijkamp, Diederik P. Kingma, Zhen Xu, Andrew M. Dai, Ying Nian Wu

Figure 1 for Flow Contrastive Estimation of Energy-Based Models
Figure 2 for Flow Contrastive Estimation of Energy-Based Models
Figure 3 for Flow Contrastive Estimation of Energy-Based Models
Figure 4 for Flow Contrastive Estimation of Energy-Based Models

  Access Paper or Ask Questions

Representation Learning: A Statistical Perspective


Nov 26, 2019
Jianwen Xie, Ruiqi Gao, Erik Nijkamp, Song-Chun Zhu, Ying Nian Wu

Figure 1 for Representation Learning: A Statistical Perspective
Figure 2 for Representation Learning: A Statistical Perspective
Figure 3 for Representation Learning: A Statistical Perspective
Figure 4 for Representation Learning: A Statistical Perspective
* Annual Review of Statistics and Its Application 2020 
  Access Paper or Ask Questions