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 24 of 29

1151. NeurIPS 2024Policy Aggregation
1152. NeurIPS 2024Predicting the Performance of Foundation Models via Agreement-on-the-Line
1153. NeurIPS 2024Preference Alignment with Flow Matching
1154. NeurIPS 2024Preference Learning Algorithms Do Not Learn Preference Rankings
1155. NeurIPS 2024Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
1156. NeurIPS 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
1157. NeurIPS 2024ProgressGym: Alignment with a Millennium of Moral Progress
1158. NeurIPS 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
1159. NeurIPS 2024ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
1160. NeurIPS 2024Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
1161. NeurIPS 2024Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
1162. NeurIPS 2024Provably Safe Neural Network Controllers via Differential Dynamic Logic
1163. NeurIPS 2024PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
1164. NeurIPS 2024Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
1165. NeurIPS 2024Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
1166. NeurIPS 2024Query-Based Adversarial Prompt Generation
1167. NeurIPS 2024RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
1168. NeurIPS 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
1169. NeurIPS 2024RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
1170. NeurIPS 2024Rapid Plug-in Defenders
1171. NeurIPS 2024RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
1172. NeurIPS 2024Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
1173. NeurIPS 2024RedCode: Multi-dimensional Safety Benchmark for Code Agents
1174. NeurIPS 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agents
1175. NeurIPS 2024Refusal in Language Models Is Mediated by a Single Direction
1176. NeurIPS 2024Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
1177. NeurIPS 2024Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
1178. NeurIPS 2024Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference
1179. NeurIPS 2024Relational Verification Leaps Forward with RABBit
1180. NeurIPS 2024ReMoDetect: Reward Models Recognize Aligned LLM's Generations
1181. NeurIPS 2024Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
1182. NeurIPS 2024Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
1183. NeurIPS 2024Rethinking LLM Memorization through the Lens of Adversarial Compression
1184. NeurIPS 2024Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
1185. NeurIPS 2024Revisiting Few-Shot Object Detection with Vision-Language Models
1186. NeurIPS 2024Risk-Averse Fine-tuning of Large Language Models
1187. NeurIPS 2024Robust Conformal Prediction Using Privileged Information
1188. NeurIPS 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
1189. NeurIPS 2024Robust Reinforcement Learning from Corrupted Human Feedback
1190. NeurIPS 2024RTify: Aligning Deep Neural Networks with Human Behavioral Decisions
1191. NeurIPS 2024Rule Based Rewards for Language Model Safety
1192. NeurIPS 2024Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
1193. NeurIPS 2024SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
1194. NeurIPS 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
1195. NeurIPS 2024SafeWorld: Geo-Diverse Safety Alignment
1196. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
1197. NeurIPS 2024Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
1198. NeurIPS 2024Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
1199. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
1200. NeurIPS 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganography

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.