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 25 of 29

1201. NeurIPS 2024Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
1202. NeurIPS 2024SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
1203. NeurIPS 2024Selective Generation for Controllable Language Models
1204. NeurIPS 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
1205. NeurIPS 2024Self-Calibrating Conformal Prediction
1206. NeurIPS 2024Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
1207. NeurIPS 2024Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
1208. NeurIPS 2024SelfCodeAlign: Self-Alignment for Code Generation
1209. NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
1210. NeurIPS 2024Sequential Harmful Shift Detection Without Labels
1211. NeurIPS 2024SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
1212. NeurIPS 2024SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
1213. NeurIPS 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
1214. NeurIPS 2024Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
1215. NeurIPS 2024SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
1216. NeurIPS 2024SimPO: Simple Preference Optimization with a Reference-Free Reward
1217. NeurIPS 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
1218. NeurIPS 2024Soft-Label Integration for Robust Toxicity Classification
1219. NeurIPS 2024Spectral Editing of Activations for Large Language Model Alignment
1220. NeurIPS 2024SpeechAlign: Aligning Speech Generation to Human Preferences
1221. NeurIPS 2024SSDM: Scalable Speech Dysfluency Modeling
1222. NeurIPS 2024Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
1223. NeurIPS 2024Stepwise Alignment for Constrained Language Model Policy Optimization
1224. NeurIPS 2024Stress-Testing Capability Elicitation With Password-Locked Models
1225. NeurIPS 2024Studying How to Efficiently and Effectively Guide Models with Explanations - A Reproducibility Study
1226. NeurIPS 2024T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
1227. NeurIPS 2024Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
1228. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
1229. NeurIPS 2024Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
1230. NeurIPS 2024Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
1231. NeurIPS 2024TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
1232. NeurIPS 2024The Art of Saying No: Contextual Noncompliance in Language Models
1233. NeurIPS 2024The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
1234. NeurIPS 2024The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
1235. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
1236. NeurIPS 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
1237. NeurIPS 2024TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
1238. NeurIPS 2024TopoFR: A Closer Look at Topology Alignment on Face Recognition
1239. NeurIPS 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
1240. NeurIPS 2024Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
1241. NeurIPS 2024Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
1242. NeurIPS 2024Transfer Q-star : Principled Decoding for LLM Alignment
1243. NeurIPS 2024Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
1244. NeurIPS 2024Transferable Adversarial Attacks on SAM and Its Downstream Models
1245. NeurIPS 2024Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
1246. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
1247. NeurIPS 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
1248. NeurIPS 2024Truth is Universal: Robust Detection of Lies in LLMs
1249. NeurIPS 2024UltraMedical: Building Specialized Generalists in Biomedicine
1250. NeurIPS 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vector

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.