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 Stefano Ermon

Stefano Ermon

Improving Compositionality of Neural Networks by Decoding Representations to Inputs


Jun 01, 2021
Mike Wu, Noah Goodman, Stefano Ermon

Figure 1 for Improving Compositionality of Neural Networks by Decoding Representations to Inputs
Figure 2 for Improving Compositionality of Neural Networks by Decoding Representations to Inputs
Figure 3 for Improving Compositionality of Neural Networks by Decoding Representations to Inputs
Figure 4 for Improving Compositionality of Neural Networks by Decoding Representations to Inputs
* 9 pages content; 2 pages appendix 
  Access Paper or Ask Questions

Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information


Apr 19, 2021
Willie Neiswanger, Ke Alexander Wang, Stefano Ermon

Figure 1 for Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Figure 2 for Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Figure 3 for Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Figure 4 for Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information

  Access Paper or Ask Questions

On the Critical Role of Conventions in Adaptive Human-AI Collaboration


Apr 07, 2021
Andy Shih, Arjun Sawhney, Jovana Kondic, Stefano Ermon, Dorsa Sadigh

Figure 1 for On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Figure 2 for On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Figure 3 for On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Figure 4 for On the Critical Role of Conventions in Adaptive Human-AI Collaboration
* 9th International Conference on Learning Representations (ICLR 2021) 
  Access Paper or Ask Questions

Improved Autoregressive Modeling with Distribution Smoothing


Mar 28, 2021
Chenlin Meng, Jiaming Song, Yang Song, Shengjia Zhao, Stefano Ermon

Figure 1 for Improved Autoregressive Modeling with Distribution Smoothing
Figure 2 for Improved Autoregressive Modeling with Distribution Smoothing
Figure 3 for Improved Autoregressive Modeling with Distribution Smoothing
Figure 4 for Improved Autoregressive Modeling with Distribution Smoothing
* ICLR 2021 (Oral) 
  Access Paper or Ask Questions

Anytime Sampling for Autoregressive Models via Ordered Autoencoding


Feb 23, 2021
Yilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon

Figure 1 for Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Figure 2 for Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Figure 3 for Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Figure 4 for Anytime Sampling for Autoregressive Models via Ordered Autoencoding
* Accepted by ICLR 2021 
  Access Paper or Ask Questions

Localized Calibration: Metrics and Recalibration


Feb 22, 2021
Rachel Luo, Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai, Shengjia Zhao, Stefano Ermon

Figure 1 for Localized Calibration: Metrics and Recalibration
Figure 2 for Localized Calibration: Metrics and Recalibration
Figure 3 for Localized Calibration: Metrics and Recalibration
Figure 4 for Localized Calibration: Metrics and Recalibration

  Access Paper or Ask Questions

Neural Network Compression for Noisy Storage Devices


Feb 15, 2021
Berivan Isik, Kristy Choi, Xin Zheng, Tsachy Weissman, Stefano Ermon, H. -S. Philip Wong, Armin Alaghi

Figure 1 for Neural Network Compression for Noisy Storage Devices
Figure 2 for Neural Network Compression for Noisy Storage Devices
Figure 3 for Neural Network Compression for Noisy Storage Devices
Figure 4 for Neural Network Compression for Noisy Storage Devices
* 19 pages, 9 figures 
  Access Paper or Ask Questions

Negative Data Augmentation


Feb 09, 2021
Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon

Figure 1 for Negative Data Augmentation
Figure 2 for Negative Data Augmentation
Figure 3 for Negative Data Augmentation
Figure 4 for Negative Data Augmentation
* Accepted at ICLR 2021 
  Access Paper or Ask Questions

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients


Jan 02, 2021
Chris Cundy, Stefano Ermon

Figure 1 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
Figure 2 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
Figure 3 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
Figure 4 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
* 8 pages; figure/table formatting fixed 
  Access Paper or Ask Questions

PiRank: Learning To Rank via Differentiable Sorting


Dec 12, 2020
Robin Swezey, Aditya Grover, Bruno Charron, Stefano Ermon

Figure 1 for PiRank: Learning To Rank via Differentiable Sorting
Figure 2 for PiRank: Learning To Rank via Differentiable Sorting
Figure 3 for PiRank: Learning To Rank via Differentiable Sorting
Figure 4 for PiRank: Learning To Rank via Differentiable Sorting

  Access Paper or Ask Questions

Efficient Conditional Pre-training for Transfer Learning


Dec 10, 2020
Shuvam Chakraborty, Burak Uzkent, Kumar Ayush, Kumar Tanmay, Evan Sheehan, Stefano Ermon

Figure 1 for Efficient Conditional Pre-training for Transfer Learning
Figure 2 for Efficient Conditional Pre-training for Transfer Learning
Figure 3 for Efficient Conditional Pre-training for Transfer Learning
Figure 4 for Efficient Conditional Pre-training for Transfer Learning

  Access Paper or Ask Questions

Geography-Aware Self-Supervised Learning


Dec 02, 2020
Kumar Ayush, Burak Uzkent, Chenlin Meng, Kumar Tanmay, Marshall Burke, David Lobell, Stefano Ermon

Figure 1 for Geography-Aware Self-Supervised Learning
Figure 2 for Geography-Aware Self-Supervised Learning
Figure 3 for Geography-Aware Self-Supervised Learning
Figure 4 for Geography-Aware Self-Supervised Learning

  Access Paper or Ask Questions

Score-Based Generative Modeling through Stochastic Differential Equations


Nov 26, 2020
Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole

Figure 1 for Score-Based Generative Modeling through Stochastic Differential Equations
Figure 2 for Score-Based Generative Modeling through Stochastic Differential Equations
Figure 3 for Score-Based Generative Modeling through Stochastic Differential Equations
Figure 4 for Score-Based Generative Modeling through Stochastic Differential Equations

  Access Paper or Ask Questions

Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration


Nov 15, 2020
Shengjia Zhao, Stefano Ermon

Figure 1 for Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
Figure 2 for Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
Figure 3 for Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
Figure 4 for Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration

  Access Paper or Ask Questions

Autoregressive Score Matching


Oct 24, 2020
Chenlin Meng, Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon

Figure 1 for Autoregressive Score Matching
Figure 2 for Autoregressive Score Matching
Figure 3 for Autoregressive Score Matching
Figure 4 for Autoregressive Score Matching
* NeurIPS 2020 
  Access Paper or Ask Questions

Probabilistic Circuits for Variational Inference in Discrete Graphical Models


Oct 22, 2020
Andy Shih, Stefano Ermon

Figure 1 for Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Figure 2 for Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Figure 3 for Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Figure 4 for Probabilistic Circuits for Variational Inference in Discrete Graphical Models
* In Advances in Neural Information Processing Systems 34 (NeurIPS), 2020 
  Access Paper or Ask Questions

Imitation with Neural Density Models


Oct 19, 2020
Kuno Kim, Akshat Jindal, Yang Song, Jiaming Song, Yanan Sui, Stefano Ermon

Figure 1 for Imitation with Neural Density Models
Figure 2 for Imitation with Neural Density Models
Figure 3 for Imitation with Neural Density Models
Figure 4 for Imitation with Neural Density Models

  Access Paper or Ask Questions

Denoising Diffusion Implicit Models


Oct 06, 2020
Jiaming Song, Chenlin Meng, Stefano Ermon

Figure 1 for Denoising Diffusion Implicit Models
Figure 2 for Denoising Diffusion Implicit Models
Figure 3 for Denoising Diffusion Implicit Models
Figure 4 for Denoising Diffusion Implicit Models

  Access Paper or Ask Questions

Understanding Classifier Mistakes with Generative Models


Oct 05, 2020
Laëtitia Shao, Yang Song, Stefano Ermon

Figure 1 for Understanding Classifier Mistakes with Generative Models
Figure 2 for Understanding Classifier Mistakes with Generative Models
Figure 3 for Understanding Classifier Mistakes with Generative Models
Figure 4 for Understanding Classifier Mistakes with Generative Models
* 17 pages, 10 figures. Submitted to ICLR2021 
  Access Paper or Ask Questions

Using satellite imagery to understand and promote sustainable development


Sep 23, 2020
Marshall Burke, Anne Driscoll, David B. Lobell, Stefano Ermon

Figure 1 for Using satellite imagery to understand and promote sustainable development
Figure 2 for Using satellite imagery to understand and promote sustainable development
Figure 3 for Using satellite imagery to understand and promote sustainable development
Figure 4 for Using satellite imagery to understand and promote sustainable development

  Access Paper or Ask Questions

Privacy Preserving Recalibration under Domain Shift


Aug 21, 2020
Rachel Luo, Shengjia Zhao, Jiaming Song, Jonathan Kuck, Stefano Ermon, Silvio Savarese

Figure 1 for Privacy Preserving Recalibration under Domain Shift
Figure 2 for Privacy Preserving Recalibration under Domain Shift
Figure 3 for Privacy Preserving Recalibration under Domain Shift
Figure 4 for Privacy Preserving Recalibration under Domain Shift

  Access Paper or Ask Questions

HiPPO: Recurrent Memory with Optimal Polynomial Projections


Aug 17, 2020
Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, Christopher Re

Figure 1 for HiPPO: Recurrent Memory with Optimal Polynomial Projections
Figure 2 for HiPPO: Recurrent Memory with Optimal Polynomial Projections
Figure 3 for HiPPO: Recurrent Memory with Optimal Polynomial Projections
Figure 4 for HiPPO: Recurrent Memory with Optimal Polynomial Projections

  Access Paper or Ask Questions

Multi-label Contrastive Predictive Coding


Jul 20, 2020
Jiaming Song, Stefano Ermon

Figure 1 for Multi-label Contrastive Predictive Coding
Figure 2 for Multi-label Contrastive Predictive Coding
Figure 3 for Multi-label Contrastive Predictive Coding
Figure 4 for Multi-label Contrastive Predictive Coding

  Access Paper or Ask Questions

Efficient Learning of Generative Models via Finite-Difference Score Matching


Jul 07, 2020
Tianyu Pang, Kun Xu, Chongxuan Li, Yang Song, Stefano Ermon, Jun Zhu

Figure 1 for Efficient Learning of Generative Models via Finite-Difference Score Matching
Figure 2 for Efficient Learning of Generative Models via Finite-Difference Score Matching
Figure 3 for Efficient Learning of Generative Models via Finite-Difference Score Matching
Figure 4 for Efficient Learning of Generative Models via Finite-Difference Score Matching

  Access Paper or Ask Questions

Individual Calibration with Randomized Forecasting


Jul 05, 2020
Shengjia Zhao, Tengyu Ma, Stefano Ermon

Figure 1 for Individual Calibration with Randomized Forecasting
Figure 2 for Individual Calibration with Randomized Forecasting
Figure 3 for Individual Calibration with Randomized Forecasting
Figure 4 for Individual Calibration with Randomized Forecasting

  Access Paper or Ask Questions

Belief Propagation Neural Networks


Jul 01, 2020
Jonathan Kuck, Shuvam Chakraborty, Hao Tang, Rachel Luo, Jiaming Song, Ashish Sabharwal, Stefano Ermon

Figure 1 for Belief Propagation Neural Networks
Figure 2 for Belief Propagation Neural Networks
Figure 3 for Belief Propagation Neural Networks
Figure 4 for Belief Propagation Neural Networks

  Access Paper or Ask Questions

Unsupervised Calibration under Covariate Shift


Jun 29, 2020
Anusri Pampari, Stefano Ermon

Figure 1 for Unsupervised Calibration under Covariate Shift
Figure 2 for Unsupervised Calibration under Covariate Shift
Figure 3 for Unsupervised Calibration under Covariate Shift
Figure 4 for Unsupervised Calibration under Covariate Shift
* Submitted to Conference on Uncertainty in Artificial Intelligence (UAI 2020) 
  Access Paper or Ask Questions