NeurIPS 2021 paper list

NeurIPS 2021 accepted paper list

Online false discovery rate control for anomaly detection in time series
Conformal Time-series Forecasting
Probabilistic Forecasting: A Level-Set Approach
Topological Attention for Time Series Forecasting
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction
Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
Dynamical Wasserstein Barycenters for Time-series Modeling

Heavy Ball Neural Ordinary Differential Equations
A Probabilistic State Space Model for Joint Inference from Differential Equations and Data
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
Multiwavelet-based Operator Learning for Differential Equations
Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations
Dynamic Resolution Network
SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems
Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling
Online Control of Unknown Time-Varying Dynamical Systems
Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems
Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions
Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features

Predicting Molecular Conformation via Dynamic Graph Score Matching
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
Diffusion Models Beat GANs on Image Synthesis
Local Hyper-Flow Diffusion
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
Structured Denoising Diffusion Models in Discrete State-Spaces
D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation
Maximum Likelihood Training of Score-Based Diffusion Models
On Density Estimation with Diffusion Models
Diffusion Normalizing Flow
A Variational Perspective on Diffusion-Based Generative Models and Score Matching
Arbitrary Conditional Distributions with Energy
Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
Bounds all around: training energy-based models with bidirectional bounds
Controllable and Compositional Generation with Latent-Space Energy-Based Models
Perturb-and-max-product: Sampling and learning in discrete energy-based models
Score-based Generative Neural Networks for Large-Scale Optimal Transport
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images
Score-based Generative Modeling in Latent Space

Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
Dissecting the Diffusion Process in Linear Graph Convolutional Networks
Beltrami Flow and Neural Diffusion on Graphs
Adaptive Diffusion in Graph Neural Networks