NeurIPS 2025 accepted papers on Probabilistic and scientific modeling
521 of the 5,812 papers accepted at NeurIPS 2025 (9.0%) are on Probabilistic and scientific modeling, compared with 8.6% at NeurIPS 2024. They fall into 8 topics.
See NeurIPS 2025 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 · 163 papers
- PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (18 citations)
- BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models (9 citations)
- NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models (8 citations)
- MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform (6 citations)
- Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data (5 citations)
- Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling (4 citations)
- From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models (4 citations)
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach (3 citations)
- Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration (3 citations)
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment (3 citations)
- CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design (2 citations)
- MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks (2 citations)
and 151 more in the interactive map.
Dynamical systems · 85 papers
- Real-Time Execution of Action Chunking Flow Policies (7 citations)
- Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models (4 citations)
- Stable Port-Hamiltonian Neural Networks (4 citations)
- Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge (3 citations)
- REMI: Reconstructing Episodic Memory During Internally Driven Path Planning (3 citations)
- FlashMD: long-stride, universal prediction of molecular dynamics (2 citations)
- From Synapses to Dynamics: Obtaining Function from Structure in a Connectome Constrained Model of the Head Direction Circuit (2 citations)
- Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations (2 citations)
- High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model (2 citations)
- Information-Driven Design of Imaging Systems (2 citations)
- Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks (1 citation)
- Characterizing control between interacting subsystems with deep Jacobian estimation (1 citation)
and 73 more in the interactive map.
Variational and generative sampling · 68 papers
- $\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models (1 citation)
- Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling (1 citation)
- Gradient Variance Reveals Failure Modes in Flow-Based Generative Models (1 citation)
- Large Language Bayes (1 citation)
- On scalable and efficient training of diffusion samplers (1 citation)
- On the Relation between Rectified Flows and Optimal Transport (1 citation)
- Path Gradients after Flow Matching (1 citation)
- A Black-Box Debiasing Framework for Conditional Sampling
- A Latent Multilayer Graphical Model For Complex, Interdependent Systems
- Amortized Sampling with Transferable Normalizing Flows
- Asymptotically exact variational flows via involutive MCMC kernels
- Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling
and 56 more in the interactive map.
Uncertainty and Gaussian processes · 57 papers
- ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition (1 citation)
- Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation (1 citation)
- Distance-informed Neural Processes (1 citation)
- Knowledge Distillation of Uncertainty using Deep Latent Factor Model (1 citation)
- Multilevel neural simulation-based inference (1 citation)
- Rethinking Approximate Gaussian Inference in Classification (1 citation)
- Torch-Uncertainty: Deep Learning Uncertainty Quantification (1 citation)
- An Adaptive Quantum Circuit of Dempster's Rule of Combination for Uncertain Pattern Classification
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- Balanced Active Inference
- Bernstein–von Mises for Adaptively Collected Data
- CoLT: The conditional localization test for assessing the accuracy of neural posterior estimates
and 45 more in the interactive map.
Causal discovery · 51 papers
- Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization (2 citations)
- Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning (1 citation)
- Causally Reliable Concept Bottleneck Models (1 citation)
- CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations (1 citation)
- Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning (1 citation)
- Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data (1 citation)
- Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders (1 citation)
- Performative Validity of Recourse Explanations (1 citation)
- Root Cause Analysis of Outliers with Missing Structural Knowledge (1 citation)
- UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems (1 citation)
- A Counterfactual Semantics for Hybrid Dynamical Systems
- A Hierarchy of Graphical Models for Counterfactual Inferences
and 39 more in the interactive map.
Differential equations and PDEs · 48 papers
- Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective (16 citations)
- Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints (4 citations)
- FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks (2 citations)
- Learning to Insert for Constructive Neural Vehicle Routing Solver (2 citations)
- Axial Neural Networks for Dimension-Free Foundation Models (1 citation)
- Continuous Simplicial Neural Networks (1 citation)
- Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis (1 citation)
- Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary (1 citation)
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization (1 citation)
- A Physics-preserved Transfer Learning Method for Differential Equations
- A Plug-and-Play Query Synthesis Active Learning Framework for Neural PDE Solvers
- AneuG-Flow: A Large-Scale Synthetic Dataset of Diverse Intracranial Aneurysm Geometries and Hemodynamics
and 36 more in the interactive map.
Treatment effects · 30 papers
- Beyond the Average: Distributional Causal Inference under Imperfect Compliance (1 citation)
- LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding (1 citation)
- A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal Inference
- A Unified Framework for the Transportability of Population-Level Causal Measures
- Adaptive Data-Borrowing for Improving Treatment Effect Estimation using External Controls
- An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation
- Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
- CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
- Conformal Prediction for Causal Effects of Continuous Treatments
- Coupling Generative Modeling and an Autoencoder with the Causal Bridge
- Data Fusion for Partial Identification of Causal Effects
- Demystifying Spectral Feature Learning for Instrumental Variable Regression
and 18 more in the interactive map.
Bayesian optimization · 19 papers
- BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem (2 citations)
- BayeSQP: Bayesian Optimization through Sequential Quadratic Programming (1 citation)
- Exploring and Exploiting Model Uncertainty in Bayesian Optimization (1 citation)
- Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning (1 citation)
- ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge (1 citation)
- Amortized Active Generation of Pareto Sets
- Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble
- Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
- Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
- DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization
- FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization
and 7 more in the interactive map.