NeurIPS 2026 accepted papers on Probabilistic and scientific modeling
543 of the 6,080 papers accepted at NeurIPS 2026 (8.9%) are on Probabilistic and scientific modeling, compared with 9.0% at NeurIPS 2025. They fall into 8 topics.
See NeurIPS 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Molecules and proteins · 129 papers
- Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics (1 citation)
- FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning (1 citation)
- Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks (1 citation)
- ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins (1 citation)
- Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
- AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift
- Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
- Atom-level Protein Representation Learning Improves Protein Structure Prediction
- Balancing Frequencies and Pixels in Flow Matching
- Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
- BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics
- Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
and 117 more in the interactive map.
Variational and generative sampling · 109 papers
- A Theory on Flow Matching with Neural Networks
- Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
- Analytical Correction for Subsampling Bias in Drifting Models
- Annealing in variational inference mitigates mode collapse: a theoretical study on Gaussian mixtures
- Beckmann Transport Models: From Autonomous Flows to One-Step Maps
- Beyond ICA: Identifiability by Symmetry Breaking
- Bridge Graphical Models: Coupling, Projection, and Current-Preserving Dynamics for Generative Modeling
- CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
- Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
- Coreset-Induced Conditional Velocity Flow Matching
- Density-Ratio Losses for Post-Hoc Learning to Defer
- Diffusion-warm sampling of the XY model enables fast thermalization at scale
and 97 more in the interactive map.
Dynamical systems · 86 papers
- Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions (1 citation)
- A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
- A simple model of co-emergence of grid and place fields
- Accuracy of Noise Ceiling Estimators for Brain Scores
- Beyond DSA: Conjugacy-based Comparison of Dynamical Systems
- BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction
- Closing the Approximation Gap in Simulation-free Latent SDEs
- Conservative Continuous-Time Treatment Optimization
- Continuity Laws for Sequential Models
- Decomposing the modulation of interactions between neuronal populations
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics
- End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
and 74 more in the interactive map.
Causal discovery · 69 papers
- Controllable Generative Sandbox for Causal Inference (1 citation)
- Causal Abstractions, Categorically Unified
- Causal Discovery via Transformed Low-Rank Quantile Surfaces
- Causal learning with the invariance principle
- Causal Representation Learning for Generalisable Recommendation
- Causality can systematically address the monsters under the bench(marks)
- Coarsening Linear Non-Gaussian Causal Models with Cycles
- Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation
- Covariate-Adjusted Deep Causal Learning for Heterogeneous Panel Data Models
- Deep Gaussian Processes on Directed Acyclic Graphs
- Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
- DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
and 57 more in the interactive map.
Differential equations and PDEs · 52 papers
- Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet (2 citations)
- Coupled Integral PINN for Discontinuity (1 citation)
- Adaptive Coordinate Transforms for Neural Operators
- Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics
- Breakeven complexity: A new perspective on neural partial differential equation solvers
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows
- Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency
- Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulators
- Efficient Generative Transformer Operators for Million-Point PDEs
- GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
- Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
- In-Context Multi-Operator Learning with DeepOSets
and 40 more in the interactive map.
Uncertainty and Gaussian processes · 46 papers
- Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters (1 citation)
- Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
- Affine Tracing: A New Paradigm for Probabilistic Linear Solvers
- Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
- Bayesian Additive Distribution Regression
- Conditioning Gaussian Processes on Almost Anything
- Consistent Bayesian Spatial Domain Partitioning Using Predictive Spanning Tree Methods
- Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method
- Flexible Routing via Uncertainty Decomposition
- Heteroscedastic Variational Last Layers
- Maximin Robust Bayesian Experimental Design
and 34 more in the interactive map.
Bayesian optimization · 26 papers
- Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
- Bayesian Decision Making around Experts
- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
- BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability
- Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
- DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization
- GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization
- In-Context Black-Box Optimization with Unreliable Feedback
- Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
- Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
- Post-ADC Inference: Valid Inference After Active Data Collection
- Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
and 14 more in the interactive map.
Treatment effects · 26 papers
- Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
- B-CALM: Bias-Limited Bayesian Borrowing for RCT-Anchored Treatment Effects under Covariate Mismatch
- Causal Evaluation of Membership Inference Attacks
- Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates
- Controlling for Omitted Variable Bias in Deep Neural Networks
- CUVET: A Partitioning Approach for Continuous Treatment Assignment At Scale
- DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments
- Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation
- Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection
- Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
- Generalized Bayes for Causal Inference
- Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects
and 14 more in the interactive map.