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

438 papers, page 8 of 9

351. NeurIPS 2023Is RLHF More Difficult than Standard RL? A Theoretical Perspective
352. NeurIPS 2023Jailbroken: How Does LLM Safety Training Fail?
353. NeurIPS 2023Language Model Alignment with Elastic Reset
354. NeurIPS 2023Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
355. NeurIPS 2023Large Language Models Are Zero-Shot Time Series Forecasters
356. NeurIPS 2023Latent Space Translation via Semantic Alignment
357. NeurIPS 2023Learning better with Dale’s Law: A Spectral Perspective
358. NeurIPS 2023Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment
359. NeurIPS 2023Learning from Active Human Involvement through Proxy Value Propagation
360. NeurIPS 2023Mass-Producing Failures of Multimodal Systems with Language Models
361. NeurIPS 2023Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
362. NeurIPS 2023Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees
363. NeurIPS 2023Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
364. NeurIPS 2023MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues
365. NeurIPS 2023Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming
366. NeurIPS 2023Neural (Tangent Kernel) Collapse
367. NeurIPS 2023Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning
368. NeurIPS 2023On Learning Necessary and Sufficient Causal Graphs
369. NeurIPS 2023On Masked Pre-training and the Marginal Likelihood
370. NeurIPS 2023On Private and Robust Bandits
371. NeurIPS 2023On skip connections and normalisation layers in deep optimisation
372. NeurIPS 2023On the impact of activation and normalization in obtaining isometric embeddings at initialization
373. NeurIPS 2023On the Interplay between Social Welfare and Tractability of Equilibria
374. NeurIPS 2023On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
375. NeurIPS 2023OpenAssistant Conversations - Democratizing Large Language Model Alignment
376. NeurIPS 2023OpenProteinSet: Training data for structural biology at scale
377. NeurIPS 2023Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
378. NeurIPS 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
379. NeurIPS 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
380. NeurIPS 2023Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
381. NeurIPS 2023Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
382. NeurIPS 2023Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
383. NeurIPS 2023Red Teaming Deep Neural Networks with Feature Synthesis Tools
384. NeurIPS 2023Regret Matching+: (In)Stability and Fast Convergence in Games
385. NeurIPS 2023Residual Alignment: Uncovering the Mechanisms of Residual Networks
386. NeurIPS 2023Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning
387. NeurIPS 2023Responsible AI (RAI) Games and Ensembles
388. NeurIPS 2023Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union
389. NeurIPS 2023Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery
390. NeurIPS 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
391. NeurIPS 2023Robust covariance estimation with missing values and cell-wise contamination
392. NeurIPS 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity
393. NeurIPS 2023RRHF: Rank Responses to Align Language Models with Human Feedback
394. NeurIPS 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
395. NeurIPS 2023SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations
396. NeurIPS 2023Safety Verification of Decision-Tree Policies in Continuous Time
397. NeurIPS 2023Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
398. NeurIPS 2023Self-supervised video pretraining yields robust and more human-aligned visual representations
399. NeurIPS 2023Sequential Predictive Two-Sample and Independence Testing
400. NeurIPS 2023Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback

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.