Alignment and Safety papers, 2023–2026

Key findings

• Alignment and Safety went from 438 papers in 2023 to 1,882 in 2026, roughly 4.3x in three years.
• NeurIPS publishes the most Alignment and Safety work: 1,421 papers from 2023 to 2026, 31% of the four-venue total.
• The fastest-growing overlap is with Social aspects · safety: papers tagged with both rose from 0 in 2023 to 137 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #1 by 2026 paper count; the fastest grower in the group, Social aspects · safety, is up 93x versus 4.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
• ICML 2026AICrypto: Evaluating Cryptography Capabilities of Large Language Models
• ICLR 2026A Fair Bayesian Inference through Matched Gibbs Posterior
• CVPR 2026Advancing Cancer Prognosis with Hierarchical Fusion of Genomic Proteomic and
• NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
• ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
• ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
• CVPR 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models
• NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
• ICML 2024A Global Geometric Analysis of Maximal Coding Rate Reduction
• ICLR 2024A unique M-pattern for micro-expression spotting in long videos
• CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
• ICML 2023A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
• ICLR 2023Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
• CVPR 2023Adjustment and Alignment for Unbiased Open Set Domain Adaptation
• NeurIPS 2026$\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning
• ICML 2026Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
• ICLR 2026A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
• CVPR 2026AlignPose Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

All Alignment and Safety papers

1,421 papers, page 28 of 29

1351. NeurIPS 2023On Learning Necessary and Sufficient Causal Graphs
1352. NeurIPS 2023On Masked Pre-training and the Marginal Likelihood
1353. NeurIPS 2023On Private and Robust Bandits
1354. NeurIPS 2023On skip connections and normalisation layers in deep optimisation
1355. NeurIPS 2023On the impact of activation and normalization in obtaining isometric embeddings at initialization
1356. NeurIPS 2023On the Interplay between Social Welfare and Tractability of Equilibria
1357. NeurIPS 2023On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
1358. NeurIPS 2023OpenAssistant Conversations - Democratizing Large Language Model Alignment
1359. NeurIPS 2023OpenProteinSet: Training data for structural biology at scale
1360. NeurIPS 2023Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
1361. NeurIPS 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
1362. NeurIPS 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
1363. NeurIPS 2023Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
1364. NeurIPS 2023Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
1365. NeurIPS 2023Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
1366. NeurIPS 2023Red Teaming Deep Neural Networks with Feature Synthesis Tools
1367. NeurIPS 2023Regret Matching+: (In)Stability and Fast Convergence in Games
1368. NeurIPS 2023Residual Alignment: Uncovering the Mechanisms of Residual Networks
1369. NeurIPS 2023Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning
1370. NeurIPS 2023Responsible AI (RAI) Games and Ensembles
1371. NeurIPS 2023Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union
1372. NeurIPS 2023Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery
1373. NeurIPS 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
1374. NeurIPS 2023Robust covariance estimation with missing values and cell-wise contamination
1375. NeurIPS 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity
1376. NeurIPS 2023RRHF: Rank Responses to Align Language Models with Human Feedback
1377. NeurIPS 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
1378. NeurIPS 2023SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations
1379. NeurIPS 2023Safety Verification of Decision-Tree Policies in Continuous Time
1380. NeurIPS 2023Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
1381. NeurIPS 2023Self-supervised video pretraining yields robust and more human-aligned visual representations
1382. NeurIPS 2023Sequential Predictive Two-Sample and Independence Testing
1383. NeurIPS 2023Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback
1384. NeurIPS 2023SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction
1385. NeurIPS 2023SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
1386. NeurIPS 2023SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data
1387. NeurIPS 2023Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm
1388. NeurIPS 2023Stability of Random Forests and Coverage of Random-Forest Prediction Intervals
1389. NeurIPS 2023Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits
1390. NeurIPS 2023Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference
1391. NeurIPS 2023StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
1392. NeurIPS 2023Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis
1393. NeurIPS 2023Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk
1394. NeurIPS 2023Strong and Precise Modulation of Human Percepts via Robustified ANNs
1395. NeurIPS 2023Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
1396. NeurIPS 2023Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
1397. NeurIPS 2023The Behavior and Convergence of Local Bayesian Optimization
1398. NeurIPS 2023The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games
1399. NeurIPS 2023The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
1400. NeurIPS 2023Theoretical and Practical Perspectives on what Influence Functions Do

FAQ

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

4,558 in total: 438 in 2023, 875 in 2024, 1,363 in 2025, 1,882 in 2026.

How many Alignment and Safety papers are at NeurIPS 2026?

NeurIPS 2026 has 480 Alignment and Safety papers, versus 455 the year before.

How many Alignment and Safety papers are at ICLR 2026?

ICLR 2026 has 623 Alignment and Safety papers, versus 473 the year before.

How many Alignment and Safety papers are at ICML 2026?

ICML 2026 has 551 Alignment and Safety papers, versus 300 the year before.

How many Alignment and Safety papers are at CVPR 2026?

CVPR 2026 has 228 Alignment and Safety papers, versus 135 the year before.

Which conference publishes the most Alignment and Safety papers?

NeurIPS, with 1,421 papers from 2023 to 2026.