AAAI 2025 accepted papers on Probabilistic and scientific modeling
165 of the 3,486 papers accepted at AAAI 2025 (4.7%) are on Probabilistic and scientific modeling, compared with 5.6% at AAAI 2024. They fall into 8 topics.
See AAAI 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 · 66 papers
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (14 citations)
- Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science (9 citations)
- C2F-TP: A Coarse-to-Fine Denoising Framework for Uncertainty-Aware Trajectory Prediction (8 citations)
- FoldToken: Learning Protein Language via Vector Quantization and Beyond (8 citations)
- Generating Counterfactual Explanations Under Temporal Constraints (8 citations)
- Bridging Sequence-Structure Alignment in RNA Foundation Models (7 citations)
- Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion (7 citations)
- SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control (7 citations)
- VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints (7 citations)
- 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance (6 citations)
- Aerodynamic Coefficients Prediction via Cross-Attention Fusion and Physical-Informed Training (6 citations)
- Relational Neurosymbolic Markov Models (6 citations)
and 54 more in the interactive map.
Variational and generative sampling · 22 papers
- DR-VAE: Debiased and Representation-enhanced Variational Autoencoder for Collaborative Recommendation (8 citations)
- Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms (7 citations)
- Multimodal Variational Autoencoder: A Barycentric View (4 citations)
- Structural Entropy Guided Probabilistic Coding (4 citations)
- Debiased Active Learning with Variational Gradient Rectifier (2 citations)
- Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors (2 citations)
- Conditional Diffusion Models Based Conditional Independence Testing (1 citation)
- Enhanced Importance Sampling Through Latent Space Exploration in Normalizing Flows (1 citation)
- Gaussian Graphical Modelling Without Independence Assumptions for Uncentered Data (1 citation)
- On the Relationship Between Monotone and Squared Probabilistic Circuits (1 citation)
- Supervised Score-Based Modeling by Gradient Boosting (1 citation)
- A Theoretical Framework for an Efficient Normalizing Flow-Based Solution to the Electronic Schrödinger Equation
and 10 more in the interactive map.
Causal discovery · 20 papers
- SPACETIME: Causal Discovery from Non-Stationary Time Series (6 citations)
- DCILP: A Distributed Approach for Large-Scale Causal Structure Learning (5 citations)
- A Practical Approach to Causal Inference over Time (3 citations)
- Local Causal Discovery Without Causal Sufficiency (2 citations)
- Causal Explanation of Quality of Parent-Child Interactions with Multimodal Behavioral Features (Student Abstract) (1 citation)
- Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport (1 citation)
- Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness (1 citation)
- Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies (1 citation)
- A Variable Occurrence-Centric Framework for Inconsistency Handling
- Boosting Causal Structure Learning: An Asymmetric Exponential Modulation Gaussian-Based Adaptive Sample Reweighting Framework
- Causal Discovery by Interventions via Integer Programming
- Causally Consistent Normalizing Flow
and 8 more in the interactive map.
Uncertainty and Gaussian processes · 20 papers
- CUQDS: Conformal Uncertainty Quantification Under Distribution Shift for Trajectory Prediction (8 citations)
- DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation (8 citations)
- Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks (6 citations)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (5 citations)
- Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling (4 citations)
- Asynchronous Distributed Gaussian Process Regression (3 citations)
- Conformalized Interval Arithmetic with Symmetric Calibration (3 citations)
- Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks (2 citations)
- Auto Encoding Neural Process for Multi-interest Recommendation (2 citations)
- Things Machine Learning Models Know That They Don’t Know (2 citations)
- Epistemic Bellman Operators (1 citation)
- General Uncertainty Estimation with Delta Variances (1 citation)
and 8 more in the interactive map.
Bayesian optimization · 15 papers
- Decomposed Quadratization: Efficient QUBO Formulation for Learning Bayesian Network (3 citations)
- Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models (3 citations)
- Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks (3 citations)
- Multi-Objective Molecular Design Through Learning Latent Pareto Set (3 citations)
- BOIDS: High-Dimensional Bayesian Optimization via Incumbent-Guided Direction Lines and Subspace Embeddings (2 citations)
- Regional Expected Improvement for Efficient Trust Region Selection in High-Dimensional Bayesian Optimization (2 citations)
- CoffeeBoost: Gradient Boosting Native Conformal Inference for Bayesian Optimization (1 citation)
- Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits (1 citation)
- Modeling All Response Surfaces in One for Conditional Search Spaces (1 citation)
- Bayesian Optimization for Unknown Cost-Varying Variable Subsets with No-Regret Costs
- Black-Box Optimization with Implicit Constraints for Public Policy
- De Novo Molecular and Crystal Design with Latent Space Bayesian Optimization
and 3 more in the interactive map.
Differential equations and PDEs · 13 papers
- Neural Variable-Order Fractional Differential Equation Networks (9 citations)
- Efficient Training of Neural Fractional-Order Differential Equation via Adjoint Backpropagation (6 citations)
- Interpretable Solutions for Multi-Physics PDEs Using T-NNGP (6 citations)
- Symbolic Neural Ordinary Differential Equations (4 citations)
- Learning Physics Informed Neural ODEs with Partial Measurements (3 citations)
- Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation (2 citations)
- Discovering Symmetries of ODEs by Symbolic Regression (2 citations)
- Number Theoretic Accelerated Learning of Physics-Informed Neural Networks (2 citations)
- Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching (1 citation)
- How to Re-enable PDE Loss for Physical Systems Modeling Under Partial Observation (1 citation)
- Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics (1 citation)
- Semi-Implicit Neural Ordinary Differential Equations (1 citation)
and 1 more in the interactive map.
Treatment effects · 5 papers
- ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments (1 citation)
- Alleviating Dual Biases in Recommendation (Student Abstract)
- Conformal Inference of Individual Treatment Effects Using Conditional Density Estimates
- Mediation Analysis for Probabilities of Causation
- PCM Selector: Penalized Covariate-Mediator Selection Operator for Evaluating Linear Causal Effects