Causal Discovery papers, 2023–2026

Key findings

• Causal Discovery went from 59 papers in 2023 to 139 in 2026, roughly 2.4x in three years.
• NeurIPS publishes the most Causal Discovery work: 150 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with General ML · unsupervised and semisupervised learning: papers tagged with both rose from 3 in 2023 to 10 in 2026.
• Among the 5 topics under Causal and Fairness, it ranks #1 by 2026 paper count; the fastest grower in the group, Bias Mitigation, is up 1.5x versus 2.4x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Characterization of Latent Variable Causal Models Consistent with Observational Data
• ICML 2026A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
• ICLR 2026Bures Generalized Category Discovery
• CVPR 2026Learning by Analogy A Causal Framework for Compositional Generalization
• NeurIPS 2025Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
• ICML 2025Bayesian Active Learning for Bivariate Causal Discovery
• ICLR 2025A Conditional Independence Test in the Presence of Discretization
• CVPR 2025Hyperbolic Category Discovery
• NeurIPS 2024Causal Bandits for Linear Structural Equation Models
• ICML 2024Adaptive Online Experimental Design for Causal Discovery
• ICLR 2024A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
• CVPR 2024Contrastive Mean-Shift Learning for Generalized Category Discovery
• NeurIPS 2023A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models
• ICML 2023Active causal structure learning with advice
• ICLR 2023Boosting Causal Discovery via Adaptive Sample Reweighting
• CVPR 2023Intrinsic Physical Concepts Discovery With Object-Centric Predictive Models
• NeurIPS 2026Act, Validate, Adapt: Closing the Causal Discovery-Control Loop
• ICML 2026Causal Discovery for Irregularly Time Series with Consistency Guarantees
• ICLR 2026Causal Discovery in the Wild: A Voting-Theoretic Ensemble Approach
• CVPR 2026PlanaReLoc Camera Relocalization in 3D Planar Primitives via Region-Based Structure

All Causal Discovery papers

53 papers, page 1 of 2

1. NeurIPS 2026A Characterization of Latent Variable Causal Models Consistent with Observational Data
2. NeurIPS 2026Act, Validate, Adapt: Closing the Causal Discovery-Control Loop
3. NeurIPS 2026AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs
4. NeurIPS 2026Attention-Based Pretraining for Unsupervised Amortized Causal Discovery
5. NeurIPS 2026Automated Causal Effect Estimation through Self-Evolving AI
6. NeurIPS 2026Causal Abstractions, Categorically Unified
7. NeurIPS 2026Causal Discovery from Unseen Environments
8. NeurIPS 2026Causal discovery needs explicit epistemic standards
9. NeurIPS 2026Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
10. NeurIPS 2026Causal Discovery under Time-Varying Delays
11. NeurIPS 2026Causal Discovery via Transformed Low-Rank Quantile Surfaces
12. NeurIPS 2026Causal Discovery with False Positive Error Control
13. NeurIPS 2026Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal
14. NeurIPS 2026Causal learning with the invariance principle
15. NeurIPS 2026Causal Representation Learning for Generalisable Recommendation
16. NeurIPS 2026Causal Survival Forests with Negative Controls
17. NeurIPS 2026CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery
18. NeurIPS 2026Coarsening Linear Non-Gaussian Causal Models with Cycles
19. NeurIPS 2026Complementing DINO Features with Image Structure for Part Discovery
20. NeurIPS 2026Cross-Model Circuit Discovery
21. NeurIPS 2026Decision Path Tracing for Causal Analysis in Transformers
22. NeurIPS 2026Decomposing Effects in Neural Causal Models
23. NeurIPS 2026Effect-Level Validation for Causal Discovery in Interactive Telemetry
24. NeurIPS 2026Emergent representations of graphical structure in mechanistic neural models of causal judgment
25. NeurIPS 2026Fiedler-Regularized Causal Discovery for Sparse Connected DAGs
26. NeurIPS 2026From Groups to Rings: Causal Evidence for Algebraic Decomposition in Grokked Transformers
27. NeurIPS 2026Generalized Bayes for Causal Inference
28. NeurIPS 2026Identifying Structural Biases from Causal Mechanism Shifts
29. NeurIPS 2026Improving Causal Explanations
30. NeurIPS 2026Improving constraint-based discovery with robust propagation and LLM priors
31. NeurIPS 2026Incorporating Neural Network Structure in the Bayesian Learning Rule
32. NeurIPS 2026Integrating Background Knowledge for Scalable Causal Discovery
33. NeurIPS 2026Learning Causal Orderings for In-Context Tabular Prediction
34. NeurIPS 2026Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
35. NeurIPS 2026MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes
36. NeurIPS 2026MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
37. NeurIPS 2026Neural Causal Models under Markov Equivalence
38. NeurIPS 2026PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
39. NeurIPS 2026PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
40. NeurIPS 2026Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
41. NeurIPS 2026Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery
42. NeurIPS 2026RnR: a meta-solver for causal discovery in undersampled time series data
43. NeurIPS 2026SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning
44. NeurIPS 2026Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery
45. NeurIPS 2026Stable Partial Order Constraints for Temporal Causal Structure Learning
46. NeurIPS 2026Statistical Inference in Causal Partial Identification under Smooth Densities
47. NeurIPS 2026Structural Causal Bottleneck Models
48. NeurIPS 2026Towards a Universal Causal Reasoner
49. NeurIPS 2026Two-Clustering Regime of Token Dynamics in Causal Attention
50. NeurIPS 2026Underlying Functional Structure of Reinforcement Learning

FAQ

How many Causal Discovery papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

379 in total: 59 in 2023, 82 in 2024, 99 in 2025, 139 in 2026.

How many Causal Discovery papers are at NeurIPS 2026?

NeurIPS 2026 has 53 Causal Discovery papers, versus 34 the year before.

How many Causal Discovery papers are at ICLR 2026?

ICLR 2026 has 25 Causal Discovery papers, versus 27 the year before.

How many Causal Discovery papers are at ICML 2026?

ICML 2026 has 54 Causal Discovery papers, versus 31 the year before.

How many Causal Discovery papers are at CVPR 2026?

CVPR 2026 has 7 Causal Discovery papers, versus 7 the year before.

Which conference publishes the most Causal Discovery papers?

NeurIPS, with 150 papers from 2023 to 2026.