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 7 of 9

301. NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
302. NeurIPS 2023[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
303. NeurIPS 2023[Re] VAE Approximation Error: ELBO and Exponential Families
304. NeurIPS 2023A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
305. NeurIPS 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
306. NeurIPS 2023A Spectral Theory of Neural Prediction and Alignment
307. NeurIPS 2023Abide by the law and follow the flow: conservation laws for gradient flows
308. NeurIPS 2023Alignment with human representations supports robust few-shot learning
309. NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
310. NeurIPS 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
311. NeurIPS 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
312. NeurIPS 2023Behavior Alignment via Reward Function Optimization
313. NeurIPS 2023Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
314. NeurIPS 2023Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment
315. NeurIPS 2023Bridging Discrete and Backpropagation: Straight-Through and Beyond
316. NeurIPS 2023Cascading Contextual Assortment Bandits
317. NeurIPS 2023Closing the gap between the upper bound and lower bound of Adam's iteration complexity
318. NeurIPS 2023Collaborative Alignment of NLP Models
319. NeurIPS 2023Convex and Non-convex Optimization Under Generalized Smoothness
320. NeurIPS 2023Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
321. NeurIPS 2023Data-Driven Network Neuroscience: On Data Collection and Benchmark
322. NeurIPS 2023Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence
323. NeurIPS 2023Degraded Polygons Raise Fundamental Questions of Neural Network Perception
324. NeurIPS 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safety
325. NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
326. NeurIPS 2023Direct Preference-based Policy Optimization without Reward Modeling
327. NeurIPS 2023Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
328. NeurIPS 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
329. NeurIPS 2023Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
330. NeurIPS 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
331. NeurIPS 2023Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks
332. NeurIPS 2023Exact Verification of ReLU Neural Control Barrier Functions
333. NeurIPS 2023Expert load matters: operating networks at high accuracy and low manual effort
334. NeurIPS 2023Explainable and Efficient Randomized Voting Rules
335. NeurIPS 2023Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models
336. NeurIPS 2023Fast and Simple Spectral Clustering in Theory and Practice
337. NeurIPS 2023FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning
338. NeurIPS 2023Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
339. NeurIPS 2023Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
340. NeurIPS 2023GALOPA: Graph Transport Learning with Optimal Plan Alignment
341. NeurIPS 2023Generalized equivalences between subsampling and ridge regularization
342. NeurIPS 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
343. NeurIPS 2023Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
344. NeurIPS 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
345. NeurIPS 2023Honesty Is the Best Policy: Defining and Mitigating AI Deception
346. NeurIPS 2023Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
347. NeurIPS 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
348. NeurIPS 2023Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
349. NeurIPS 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
350. NeurIPS 2023IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

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.