CVPR 2026 accepted papers on Probabilistic and scientific modeling
60 of the 4,042 papers accepted at CVPR 2026 (1.5%) are on Probabilistic and scientific modeling, compared with 0.7% at CVPR 2025. They fall into 8 topics.
See CVPR 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 · 24 papers
- Perception Characteristics Distance: Measuring Stability and Robustness of Perception System in Dynamic Conditions under a Certain Decision Rule (1 citation)
- Vibe Spaces for Creatively Connecting and Expressing Visual Concepts (1 citation)
- Advancing Cancer Prognosis with Hierarchical Fusion of Genomic, Proteomic and Pathology Imaging Data from a Systems Biology Perspective
- AutoRegressive Generation with B-rep Holistic Token Sequence Representation
- AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts
- Den-TP: A Density-Balanced Data Curation and Evaluation Framework for Trajectory Prediction
- FoSS: Modeling Long-Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier-State Space Integration
- GeoWorld: Geometric World Models
- GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
- MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
- MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Prediction
- Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Prediction
and 12 more in the interactive map.
Variational and generative sampling · 13 papers
- Bidirectional Normalizing Flow: From Data to Noise and Back
- COT-FM: Cluster-wise Optimal Transport Flow Matching
- Functional Mean Flow in Hilbert Space
- Learning Straight Flows: Variational Flow Matching for Efficient Generation
- Mapping Networks
- Spatiotemporal Pyramid Flow Matching for Climate Emulation
- VENI: Variational Encoder for Natural Illumination
- FARMER: Flow AutoRegressive Transformer over Pixels
- Flow Matching for Multimodal Distributions
- Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
- Neural Mixture Density Processes
- Stable Mean Flow: Lyapunov-Inspired One-Step Flow Matching
and 1 more in the interactive map.
Dynamical systems · 7 papers
- BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting
- CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics
- Contact-Aware Neural Dynamics
- MRI Contrast Enhancement Kinetics World Model
- NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
- Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs
- UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching
Uncertainty and Gaussian processes · 5 papers
- Enhancing Accuracy of Uncertainty Estimation in Appearance-based Gaze Tracking with Probabilistic Evaluation and Calibration
- Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
- ReBaPL: Repulsive Bayesian Prompt Learning
- Spectral Conformal Risk Control: Distribution-Free Tail Guarantees via Bayesian Quadrature
- Towards Knowledge-augmented Bayesian Deep Learning For Computer Vision
Differential equations and PDEs · 4 papers
Causal discovery · 4 papers
- A Polynomial Chaos Framework for Causal Discovery in Nonlinear Uncertain Systems
- CGU-Bayes: Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalization
- GeneVAR: Causal MeanFlow for Autoregressive Gene-to-WSI Tile Synthesis
- Learning by Analogy: A Causal Framework for Compositional Generalization