b'Stefano Ermon'

research

∙ 08/23/2023

HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing

Small farms contribute to a large share of the productive land in develo...

0 Jonathan Xu, et al. ∙

research

∙ 06/30/2023

Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions

Generating learning-friendly representations for points in space is a fu...

0 Gengchen Mai, et al. ∙

research

∙ 06/27/2023

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

Genomic (DNA) sequences encode an enormous amount of information for gen...

0 Eric Nguyen, et al. ∙

research

∙ 06/08/2023

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking

In many domains, autoregressive models can achieve low log-likelihood on...

0 Chris Cundy, et al. ∙

research

∙ 06/01/2023

On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization

The emergence of various notions of “consistency” in diffusion models ha...

0 Chieh-Hsin Lai, et al. ∙

research

∙ 05/27/2023

MADiff: Offline Multi-agent Learning with Diffusion Models

Diffusion model (DM), as a powerful generative model, recently achieved ...

0 Zhengbang Zhu, et al. ∙

research

∙ 05/25/2023

Parallel Sampling of Diffusion Models

Diffusion models are powerful generative models but suffer from slow sam...

0 Andy Shih, et al. ∙

research

∙ 05/18/2023

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Achieving machine autonomy and human control often represent divergent o...

0 Can Qin, et al. ∙

research

∙ 05/02/2023

Geometric Latent Diffusion Models for 3D Molecule Generation

Generative models, especially diffusion models (DMs), have achieved prom...

0 Minkai Xu, et al. ∙

research

∙ 05/01/2023

CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations

Geo-tagged images are publicly available in large quantities, whereas la...

5 Gengchen Mai, et al. ∙

research

∙ 04/28/2023

MUDiff: Unified Diffusion for Complete Molecule Generation

We present a new model for generating molecular data by combining discre...

11 Chenqing Hua, et al. ∙

research

∙ 04/10/2023

Reflected Diffusion Models

Score-based diffusion models learn to reverse a stochastic differential ...

0 Aaron Lou, et al. ∙

research

∙ 04/10/2023

MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning

We study how a principal can efficiently and effectively intervene on th...

0 Arundhati Banerjee, et al. ∙

research

∙ 03/29/2023

Ideal Abstractions for Decision-Focused Learning

We present a methodology for formulating simplifying abstractions in mac...

0 Michael Poli, et al. ∙

research

∙ 03/23/2023

End-to-End Diffusion Latent Optimization Improves Classifier Guidance

Classifier guidance – using the gradients of an image classifier to stee...

0 Bram Wallace, et al. ∙

research

∙ 03/17/2023

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation

Text-to-image (T2I) models based on diffusion processes have achieved re...

0 Can Qin, et al. ∙

research

∙ 03/16/2023

HIVE: Harnessing Human Feedback for Instructional Visual Editing

Incorporating human feedback has been shown to be crucial to align text ...

1 Shu Zhang, et al. ∙

research

∙ 02/21/2023

Hyena Hierarchy: Towards Larger Convolutional Language Models

Recent advances in deep learning have relied heavily on the use of large...

7 Michael Poli, et al. ∙

research

∙ 02/07/2023

Long Horizon Temperature Scaling

Temperature scaling is a popular technique for tuning the sharpness of a...

0 Andy Shih, et al. ∙

research

∙ 01/30/2023

GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration

Pre-trained diffusion models have been successfully used as priors in a ...

0 Naoki Murata, et al. ∙

research

∙ 01/05/2023

Extreme Q-Learning: MaxEnt RL without Entropy

Modern Deep Reinforcement Learning (RL) algorithms require estimates of ...

0 Divyansh Garg, et al. ∙

research

∙ 01/04/2023

Building Coverage Estimation with Low-resolution Remote Sensing Imagery

Building coverage statistics provide crucial insights into the urbanizat...

5 Enci Liu, et al. ∙

research

∙ 12/24/2022

Deep Latent State Space Models for Time-Series Generation

Methods based on ordinary differential equations (ODEs) are widely used ...

0 Linqi Zhou, et al. ∙

research

∙ 11/26/2022

Transform Once: Efficient Operator Learning in Frequency Domain

Spectral analysis provides one of the most effective paradigms for infor...

9 Michael Poli, et al. ∙

research

∙ 11/03/2022

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

During image editing, existing deep generative models tend to re-synthes...

6 Muyang Li, et al. ∙

research

∙ 11/02/2022

Concrete Score Matching: Generalized Score Matching for Discrete Data

Representing probability distributions by the gradient of their density ...

6 Chenlin Meng, et al. ∙

research

∙ 10/22/2022

LMPriors: Pre-Trained Language Models as Task-Specific Priors

Particularly in low-data regimes, an outstanding challenge in machine le...

9 Kristy Choi, et al. ∙

research

∙ 10/09/2022

Regularizing Score-based Models with Score Fokker-Planck Equations

Score-based generative models learn a family of noise-conditional score ...

0 Chieh-Hsin Lai, et al. ∙

research

∙ 10/06/2022

On Distillation of Guided Diffusion Models

Classifier-free guided diffusion models have recently been shown to be h...

12 Chenlin Meng, et al. ∙

research

∙ 09/29/2022

Towards General-Purpose Representation Learning of Polygonal Geometries

Neural network representation learning for spatial data is a common need...

0 Gengchen Mai, et al. ∙

research

∙ 09/28/2022

ButterflyFlow: Building Invertible Layers with Butterfly Matrices

Normalizing flows model complex probability distributions using maps obt...

9 Chenlin Meng, et al. ∙

research

∙ 09/23/2022

JPEG Artifact Correction using Denoising Diffusion Restoration Models

Diffusion models can be used as learned priors for solving various inver...

10 Bahjat Kawar, et al. ∙

research

∙ 07/17/2022

SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery

Unsupervised pre-training methods for large vision models have shown to ...

15 Yezhen Cong, et al. ∙

research

∙ 05/27/2022

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Transformers are slow and memory-hungry on long sequences, since the tim...

10 Tri Dao, et al. ∙

research

∙ 05/26/2022

Training and Inference on Any-Order Autoregressive Models the Right Way

Conditional inference on arbitrary subsets of variables is a core proble...

3 Andy Shih, et al. ∙

research

∙ 04/15/2022

Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations

Many patterns in nature exhibit self-similarity: they can be compactly d...

5 Michael Poli, et al. ∙

research

∙ 04/04/2022

Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-Resolution

Automated tracking of urban development in areas where construction info...

1 Yutong He, et al. ∙

research

∙ 03/16/2022

Dual Diffusion Implicit Bridges for Image-to-Image Translation

Common image-to-image translation methods rely on joint training over da...

3 Xuan Su, et al. ∙

research

∙ 02/28/2022

LISA: Learning Interpretable Skill Abstractions from Language

Learning policies that effectually utilize language instructions in comp...

1 Divyansh Garg, et al. ∙

research

∙ 02/02/2022

Imitation Learning by Estimating Expertise of Demonstrators

Many existing imitation learning datasets are collected from multiple de...

11 Mark Beliaev, et al. ∙

research

∙ 01/27/2022

Denoising Diffusion Restoration Models

Many interesting tasks in image restoration can be cast as linear invers...

2 Bahjat Kawar, et al. ∙

research

∙ 01/05/2022

Conditional Imitation Learning for Multi-Agent Games

While advances in multi-agent learning have enabled the training of incr...

5 Andy Shih, et al. ∙

research

∙ 12/12/2021

Quantifying and Understanding Adversarial Examples in Discrete Input Spaces

Modern classification algorithms are susceptible to adversarial examples...

0 Volodymyr Kuleshov, et al. ∙

research

∙ 12/07/2021

A Unified Framework for Multi-distribution Density Ratio Estimation

Binary density ratio estimation (DRE), the problem of estimating the rat...

11 Lantao Yu, et al. ∙

research

∙ 12/06/2021

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

A structural equation model (SEM) is an effective framework to reason ov...

0 Chris Cundy, et al. ∙

research

∙ 12/02/2021

HyperSPNs: Compact and Expressive Probabilistic Circuits

Probabilistic circuits (PCs) are a family of generative models which all...

0 Andy Shih, et al. ∙

research

∙ 11/08/2021

SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning

Progress toward the United Nations Sustainable Development Goals (SDGs) ...

25 Christopher Yeh, et al. ∙

research

∙ 09/29/2021

Equivariant Neural Network for Factor Graphs

Several indices used in a factor graph data structure can be permuted wi...

12 Fan-Yun Sun, et al. ∙

research

∙ 07/12/2021

Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration

When facing uncertainty, decision-makers want predictions they can trust...

0 Shengjia Zhao, et al. ∙

research

∙ 07/10/2021

Multi-Agent Imitation Learning with Copulas

Multi-agent imitation learning aims to train multiple agents to perform ...

7 Hongwei Wang, et al. ∙

Stefano Ermon

Featured Co-authors