TPAMI 2025 papers on Probabilistic and scientific modeling
34 of the 932 papers published in TPAMI 2025 (3.6%) are on Probabilistic and scientific modeling, compared with 2.3% at TPAMI 2024. They fall into 7 topics.
See TPAMI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Variational and generative sampling · 8 papers
- Variational Positive-Incentive Noise: How Noise Benefits Models (104 citations)
- Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation (13 citations)
- Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration (5 citations)
- DELBO: Efficient Score Algorithm for Feature Selection on Latent Variables of VAE (5 citations)
- Unsupervised Representation Learning From Sparse Transformation Analysis (2 citations)
- Optimizing Unnormalized Statistical Models Through Compositional Optimization (1 citation)
- Scalable Random Feature Latent Variable Models (1 citation)
- Partial Distribution Matching via Partial Wasserstein Adversarial Networks
Uncertainty and Gaussian processes · 7 papers
- A Comprehensive Survey on Evidential Deep Learning and its Applications (77 citations)
- A Review of Uncertainty Representation and Quantification in Neural Networks (13 citations)
- Bayesian Variance Change Point Detection With Credible Sets (8 citations)
- Feature Preserving Shrinkage on Bayesian Neural Networks Via the R2D2 Prior (1 citation)
- A Variational Bayesian Inference Theory of Elasticity and Its Mixed Probabilistic Finite Element Method for Inverse Deformation Solutions in Any Dimension
- Revisiting Essential and Nonessential Settings of Evidential Deep Learning
- Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution
Causal discovery · 6 papers
- A Causal Adjustment Module for Debiasing Scene Graph Generation (47 citations)
- Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networks (34 citations)
- Addressing Information Asymmetry: Deep Temporal Causality Discovery for Mixed Time Series (30 citations)
- Interpreting Low-Level Vision Models With Causal Effect Maps (16 citations)
- A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation (7 citations)
- Intersecting the Markov Blankets of Endogenous and Exogenous Variables for Causal Discovery (2 citations)
Molecules and proteins · 6 papers
- WAKE: Towards Robust and Physically Feasible Trajectory Prediction for Autonomous Vehicles With WAvelet and KinEmatics Synergy (37 citations)
- Joint Short-Term Origin-Destination Demand Prediction for Multimodal Transport Systems (6 citations)
- Gaussian Mixture Conditional Variational Recurrent Neural Network for Unified Trajectory Imputation and Prediction (2 citations)
- Joint Sparse Optical Flow Estimation and Keypoint Detection via Dual-task Imperative Learning (2 citations)
- On Structuring Hyperspherical Manifold for Probing Novel Biomedical Entities (1 citation)
- Sparse Trajectory Prediction
Dynamical systems · 4 papers
- Dynamic Autoregressive Tensor Factorization for Pattern Discovery of Spatiotemporal Systems (4 citations)
- A Gravity-Informed Spatiotemporal Transformer for Human Activity Intensity Prediction (3 citations)
- Generalizing to New Dynamical Systems via Frequency Domain Adaptation (1 citation)
- Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming
