Risk Modeling papers, 2023–2026

Key findings

• Risk Modeling went from 15 papers in 2023 to 48 in 2026, roughly 3.2x in three years.
• NeurIPS publishes the most Risk Modeling work: 47 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with Reinforcement Learning: papers tagged with both rose from 4 in 2023 to 12 in 2026.
• Among the 5 topics under Finance and Economics, it ranks #1 by 2026 paper count; the fastest grower in the group, Macro Forecasting, is up 8.0x versus 3.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026CCTimeBoost: Learning Time-Varying Relative Risk with Case-Control Boosted Trees
• ICML 2026A Machine-Learned Comorbidity Index
• ICLR 2026SAFER: Risk-Constrained Sample-then-Filter in Large Language Models
• CVPR 2026Spectral Conformal Risk Control Distribution-Free Tail Guarantees via Bayesian Quadrature
• NeurIPS 2025Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks
• ICML 2025Compositional Risk Minimization
• ICLR 2025Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering
• NeurIPS 2024Evaluating language models as risk scores
• ICML 2024Differentially Private Worst-group Risk Minimization
• ICLR 2024SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
• CVPR 2024Self-Calibrating Vicinal Risk Minimisation for Model Calibration
• NeurIPS 2023Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
• ICML 2023Fast Excess Risk Rates via Offset Rademacher Complexity
• ICLR 2023Avoiding spurious correlations via logit correction
• NeurIPS 2026Hidden Tails: Certifying Tail-Risk Claims under Selective Labels
• ICML 2026Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference
• ICLR 2026Conformalized Decision Risk Assessment
• CVPR 2026CoRiM Conflict-driven Risk Minimization for Dynamic Multimodal Fusion
• NeurIPS 2025Risk Bounds For Distributional Regression
• ICML 2025Structure-informed Risk Minimization for Robust Ensemble Learning

All Risk Modeling papers

115 papers, page 1 of 3

1. CVPR 2026CoRiM Conflict-driven Risk Minimization for Dynamic Multimodal Fusion
2. CVPR 2026Roots Beneath the Cut Uncovering the Risk of Concept Revival
3. CVPR 2026Spectral Conformal Risk Control Distribution-Free Tail Guarantees via Bayesian Quadrature
4. ICLR 2026ConfHit: Conformal Generative Design via Nested Testing
5. ICLR 2026Conformalized Decision Risk Assessment
6. ICLR 2026Epistemic Uncertainty Quantification To Improve Decisions From Black-Box Models
7. ICLR 2026How Catastrophic is Your LLM? Certifying Risk in Conversation
8. ICLR 2026SAFER: Risk-Constrained Sample-then-Filter in Large Language Models
9. ICLR 2026Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
10. ICML 2026A Machine-Learned Comorbidity Index
11. ICML 2026Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
12. ICML 2026Correcting Overparameterization Effects in Fair Empirical Risk Minimization
13. ICML 2026Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling
14. ICML 2026Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference
15. ICML 2026Estimating Tail Risks in Language Model Output Distributions
16. ICML 2026Learning Anisotropic Value Geometry with Finsler Reinforcement Learning
17. ICML 2026New Wide-Net-Casting Jailbreak Attacks Risk Large Models
18. ICML 2026Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
19. ICML 2026Optimal Transport for LLM Reward Modeling from Noisy Feedback
20. ICML 2026PathwayLLM: Explainable Clinical Trajectory Modeling with Structured Pathways for Sepsis Prediction
21. ICML 2026Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
22. ICML 2026RiskZero: Plan More to Risk Less with a Learned Model
23. ICML 2026Why ReLU? A Bit-Model Dichotomy for Deep Network Training
24. NeurIPS 2026Anytime-Valid Conformal Risk Control
25. NeurIPS 2026Benchmarking Risk Attitudes of LLMs
26. NeurIPS 2026Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
27. NeurIPS 2026CCTimeBoost: Learning Time-Varying Relative Risk with Case-Control Boosted Trees
28. NeurIPS 2026CompilerKV: Risk-Adaptive KV Cache Compression via Offline Experience Compilation
29. NeurIPS 2026DiffRisk: Diffusion Representation Learning with Informative Missingness for Health Risk Prediction
30. NeurIPS 2026Distribution-First Framework for Learning Risk-Sensitive Individualized Treatment Rules
31. NeurIPS 2026Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach
32. NeurIPS 2026Finite Time Analysis of Risk-Sensitive RL via Noisy Power Iteration
33. NeurIPS 2026Hidden Tails: Certifying Tail-Risk Claims under Selective Labels
34. NeurIPS 2026KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
35. NeurIPS 2026Long-Term Risks of Risk-Based Allocation
36. NeurIPS 2026NNCoxKL: Risk-Set Distillation from Probability-Free Prognostic Teachers for Deep Cox Models
37. NeurIPS 2026Occupancy-based Quantile Risk Control
38. NeurIPS 2026Optimal Risk Bounds of Stochastic Gradient Descent for Shallow ReLU Networks
39. NeurIPS 2026Progressive Risk Estimation for Accident Anticipation
40. NeurIPS 2026Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
41. NeurIPS 2026Risk-Controlled Post-Processing of Decision Policies
42. NeurIPS 2026Risk-guided Estimation-aware Acceptance for Learning with Synthetic Data
43. NeurIPS 2026Risk-Sensitive Deep Optimal Stopping
44. NeurIPS 2026Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
45. NeurIPS 2026Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
46. NeurIPS 2026Tail-Risk-Aware Stackelberg Learning
47. NeurIPS 2026Training Generalizable Collaborative Agents via Strategic Risk Aversion
48. NeurIPS 2026WURI: Watching Unfolding Risk in Agent Interactions
49. ICLR 2025BingoGuard: LLM Content Moderation Tools with Risk Levels
50. ICLR 2025Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering

FAQ

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

115 in total: 15 in 2023, 26 in 2024, 26 in 2025, 48 in 2026.

How many Risk Modeling papers are at NeurIPS 2026?

NeurIPS 2026 has 25 Risk Modeling papers, versus 9 the year before.

How many Risk Modeling papers are at ICLR 2026?

ICLR 2026 has 6 Risk Modeling papers, versus 9 the year before.

How many Risk Modeling papers are at ICML 2026?

ICML 2026 has 14 Risk Modeling papers, versus 8 the year before.

How many Risk Modeling papers are at CVPR 2026?

CVPR 2026 has 3 Risk Modeling papers.

Which conference publishes the most Risk Modeling papers?

NeurIPS, with 47 papers from 2023 to 2026.