Deep learning · probabilistic methods papers, 2023–2026

Key findings

• Deep learning · probabilistic methods went from 107 papers in 2023 to 107 in 2026, roughly 1.0x in three years.
• NeurIPS publishes the most Deep learning · probabilistic methods work: 440 papers from 2023 to 2026, 69% of the four-venue total.
• The fastest-growing overlap is with Simulation for Driving: papers tagged with both rose from 5 in 2023 to 14 in 2026.
• Among the 11 topics under Deep Learning, it ranks #9 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 1.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Faster Algorithm for the Half-Trek Criterion in Structural Causal Models
• ICML 2026An Efficient Joint Learning Approach for Item Response Theory
• ICLR 2026Probabilistic Kernel Function for Fast Angle Testing
• CVPR 2026Beyond Text Visual Description Assembly by Probabilistic Model for CLIP-based
• NeurIPS 2025$\text{G}^2\text{M}$: A Generalized Gaussian Mirror Method to Boost Feature Selection Power
• ICML 2025Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
• ICLR 2025P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS
• CVPR 2025ProbPose: A Probabilistic Approach to 2D Human Pose Estimation
• NeurIPS 2024[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
• ICML 2024A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs
• ICLR 2024A Probabilistic Framework for Modular Continual Learning
• CVPR 2024CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation
• NeurIPS 2023A Computationally Efficient Sparsified Online Newton Method
• ICML 2023A theory of representation learning gives a deep generalisation of kernel methods
• ICLR 2023A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
• CVPR 2023Probabilistic Knowledge Distillation of Face Ensembles
• NeurIPS 2026Affine Tracing: A New Paradigm for Probabilistic Linear Solvers
• ICML 2026Avoid What You Know: Divergent Trajectory Balance for GFlowNets
• ICLR 2026Learning Survival Distributions with Individually Calibrated Asymmetric Laplace Distribution
• CVPR 2026ARES Unifying Asymmetric RGB-Event Stereo for Probabilistic Scene Flow Estimation

All Deep learning · probabilistic methods papers

59 papers, page 1 of 2

1. ICML 2026A Probabilistic Framework for LLM-Based Model Discovery
2. ICML 2026Allocating Variance to Maximize Expectation
3. ICML 2026An Efficient Joint Learning Approach for Item Response Theory
4. ICML 2026Avoid What You Know: Divergent Trajectory Balance for GFlowNets
5. ICML 2026BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields
6. ICML 2026Beyond Euclidean Summaries: Online Change Point Detection for Distribution-Valued Data
7. ICML 2026Beyond Softmax: A Natural Parameterization for Categorical Random Variables
8. ICML 2026Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE Constraints
9. ICML 2026Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
10. ICML 2026Calibrated Preference Learning: The Case of Label Ranking
11. ICML 2026Calibrating Decision Robustness via Inverse Conformal Risk Control
12. ICML 2026Colorful Pinball: Density-Weighted Quantile Regression for Conditional Guarantee of Conformal Prediction
13. ICML 2026Column Thresholding for Sparse Spiked Wigner Models: Improved Signal Strength Requirements
14. ICML 2026Conformal Calibration Transfer
15. ICML 2026Conformal Risk-Averse Decision Making with Action Conditional Guarantee
16. ICML 2026De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
17. ICML 2026Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
18. ICML 2026Error Analysis of Discrete Flow with Generator Matching
19. ICML 2026Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
20. ICML 2026From Individual Calibration to Reliable Classifiers: ALD Parameterization with mPAIC Guarantees
21. ICML 2026Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
22. ICML 2026GEM-FI: Gated Evidential Mixtures with Fisher Modulation
23. ICML 2026General Synthetic-Powered Inference
24. ICML 2026Generalized Schrödinger Bridge on Graphs
25. ICML 2026Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients
26. ICML 2026Geometry-Aware Probabilistic Circuits via Voronoi Tessellations
27. ICML 2026Incremental Transformer Neural Processes
28. ICML 2026Innovation: An Almost Characterization of Hallucination
29. ICML 2026Joint Model and Data Sparsification via the Marginal Likelihood
30. ICML 2026Latent Guided Sampling for Combinatorial Optimization
31. ICML 2026Learning to Bet for Horizon-Aware Anytime-Valid Testing
32. ICML 2026LieStoNet: Learning Lie Symmetries from Spatiotemporal Data for Stochastic Dynamical Systems
33. ICML 2026Maximum-Likelihood Learning of Latent Dynamics Without Reconstruction
34. ICML 2026Minimum Distance Summaries for Robust Neural Posterior Estimation
35. ICML 2026Monotonic Variational Gaussian Process for Efficient Data Collection
36. ICML 2026Multi-Distribution Robust Conformal Prediction
37. ICML 2026Multiple Choice Learning of Low-Rank Adapters for Language Modeling
38. ICML 2026Near-Universal Multiplicative Updates for Nonnegative Einsum Factorization
39. ICML 2026On the Epistemic Uncertainty of Overparametrized Neural Networks
40. ICML 2026Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
41. ICML 2026PPDL: LLM-Based Flows as Probabilistic Programs
42. ICML 2026Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication
43. ICML 2026Principled Confidence Estimation for Deep Computed Tomography
44. ICML 2026Probabilistic Bisection Algorithm Provably Achieves Exponential Convergence
45. ICML 2026Probabilistic Retrofitting of Learned Simulators
46. ICML 2026Probably Approximately Correct Labels
47. ICML 2026ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
48. ICML 2026Pseudo-Mallows for Efficient Probabilistic Preference Learning
49. ICML 2026Reduction of Probabilistic Chemical Reaction Networks
50. ICML 2026Revisiting Neural Processes via Fourier Transform and Volterra Series

FAQ

How many Deep learning · probabilistic methods papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

637 in total: 107 in 2023, 160 in 2024, 263 in 2025, 107 in 2026.

How many Deep learning · probabilistic methods papers are at NeurIPS 2026?

NeurIPS 2026 has 28 Deep learning · probabilistic methods papers, versus 212 the year before.

How many Deep learning · probabilistic methods papers are at ICLR 2026?

ICLR 2026 has 13 Deep learning · probabilistic methods papers, versus 10 the year before.

How many Deep learning · probabilistic methods papers are at ICML 2026?

ICML 2026 has 59 Deep learning · probabilistic methods papers, versus 37 the year before.

How many Deep learning · probabilistic methods papers are at CVPR 2026?

CVPR 2026 has 7 Deep learning · probabilistic methods papers, versus 4 the year before.

Which conference publishes the most Deep learning · probabilistic methods papers?

NeurIPS, with 440 papers from 2023 to 2026.