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 27 of 29

1301. NeurIPS 2023Collaborative Alignment of NLP Models
1302. NeurIPS 2023Convex and Non-convex Optimization Under Generalized Smoothness
1303. NeurIPS 2023Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
1304. NeurIPS 2023Data-Driven Network Neuroscience: On Data Collection and Benchmark
1305. NeurIPS 2023Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence
1306. NeurIPS 2023Degraded Polygons Raise Fundamental Questions of Neural Network Perception
1307. NeurIPS 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safety
1308. NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
1309. NeurIPS 2023Direct Preference-based Policy Optimization without Reward Modeling
1310. NeurIPS 2023Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
1311. NeurIPS 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
1312. NeurIPS 2023Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
1313. NeurIPS 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
1314. NeurIPS 2023Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks
1315. NeurIPS 2023Exact Verification of ReLU Neural Control Barrier Functions
1316. NeurIPS 2023Expert load matters: operating networks at high accuracy and low manual effort
1317. NeurIPS 2023Explainable and Efficient Randomized Voting Rules
1318. NeurIPS 2023Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models
1319. NeurIPS 2023Fast and Simple Spectral Clustering in Theory and Practice
1320. NeurIPS 2023FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning
1321. NeurIPS 2023Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
1322. NeurIPS 2023Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
1323. NeurIPS 2023GALOPA: Graph Transport Learning with Optimal Plan Alignment
1324. NeurIPS 2023Generalized equivalences between subsampling and ridge regularization
1325. NeurIPS 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
1326. NeurIPS 2023Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
1327. NeurIPS 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
1328. NeurIPS 2023Honesty Is the Best Policy: Defining and Mitigating AI Deception
1329. NeurIPS 2023Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
1330. NeurIPS 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
1331. NeurIPS 2023Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
1332. NeurIPS 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
1333. NeurIPS 2023IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers
1334. NeurIPS 2023Is RLHF More Difficult than Standard RL? A Theoretical Perspective
1335. NeurIPS 2023Jailbroken: How Does LLM Safety Training Fail?
1336. NeurIPS 2023Language Model Alignment with Elastic Reset
1337. NeurIPS 2023Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
1338. NeurIPS 2023Large Language Models Are Zero-Shot Time Series Forecasters
1339. NeurIPS 2023Latent Space Translation via Semantic Alignment
1340. NeurIPS 2023Learning better with Dale’s Law: A Spectral Perspective
1341. NeurIPS 2023Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment
1342. NeurIPS 2023Learning from Active Human Involvement through Proxy Value Propagation
1343. NeurIPS 2023Mass-Producing Failures of Multimodal Systems with Language Models
1344. NeurIPS 2023Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
1345. NeurIPS 2023Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees
1346. NeurIPS 2023Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
1347. NeurIPS 2023MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues
1348. NeurIPS 2023Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming
1349. NeurIPS 2023Neural (Tangent Kernel) Collapse
1350. NeurIPS 2023Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning

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.