Research map

Probabilistic and scientific modeling: research map

Bayesian and causal inference, uncertainty, dynamical systems, PDEs, and molecules.

8,443 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 8 topics. Within all five venues, its share held steady from 7.7% in 2023–24 to 6.7% in 2025–26 (2,034 → 3,049 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Probabilistic and scientific modeling in the interactive map

Topics

• Variational and generative sampling · 2,060 papers
  Likelihood-free and graphical model estimation, Tractable probabilistic models, Exact inference for probabilistic programs
• Molecules and proteins · 1,990 papers
  Prediction-powered and conformal inference, Statistical analysis of ML practice, Machine learning for physical simulation
• Uncertainty and Gaussian processes · 1,162 papers
  Nonparametric and PAC-Bayes Bayesian learning, Simulation-based inference, Variational Bayesian deep learning
• Dynamical systems · 969 papers
  Physics-informed dynamics learning, Latent dynamics models, Latent-space control and planning
• Causal discovery · 830 papers
  Latent-variable causal estimation, Causal effect identification, Causal representation identifiability
• Differential equations and PDEs · 614 papers
  Neural PDE solvers, Physics-informed operator learning, Neural operators for general geometries
• Treatment effects · 421 papers
  Proximal and deep causal effect estimation, Latent-variable causal inference, Instrumental variable estimation
• Bayesian optimization · 397 papers
  Acquisition function design, Local and high-dimensional Bayesian optimization, Multi-fidelity hyperparameter optimization

Most cited papers in Probabilistic and scientific modeling

• Wasserstein Generative Adversarial Networks (ICML 2017 · 4,925 citations)
• FlowNet 2.0: Evolution of Optical Flow Estimation With Deep Networks (CVPR 2017 · 3,371 citations)
• Categorical Reparameterization with Gumbel-Softmax (ICLR 2017 · 3,310 citations)
• beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (ICLR 2017 · 2,979 citations)
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (NeurIPS 2017 · 2,921 citations)
• Neural Discrete Representation Learning (NeurIPS 2017 · 2,816 citations)
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (ICML 2016 · 2,628 citations)
• Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks (CVPR 2018 · 2,462 citations)
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables (ICLR 2017 · 1,471 citations)
• Complex Embeddings for Simple Link Prediction (ICML 2016 · 1,122 citations)
• A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation (CVPR 2016 · 1,104 citations)
• Generative Modeling by Estimating Gradients of the Data Distribution (NeurIPS 2019 · 1,076 citations)