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

4,558 papers, page 25 of 92

1201. ICML 2026Per-example Gradients: a New Frontier for Understanding and Improving Optimizers
1202. ICML 2026Perceptrons and Localization of Attention’s Mean-Field Landscape
1203. ICML 2026Personalized Image Generation via Human-in-the-loop Bayesian Optimization
1204. ICML 2026PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
1205. ICML 2026PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
1206. ICML 2026PLANTAIN: Plan-Answer Interleaved Reasoning
1207. ICML 2026Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
1208. ICML 2026PoMtVRS: Preference-Optimized Multi-Task Vehicle Routing Solver with Preference Gating
1209. ICML 2026Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
1210. ICML 2026Post-Training Language Models for Crosslingual Consistency
1211. ICML 2026Post-Training with Policy Gradients: Optimality and the Base Model Barrier
1212. ICML 2026Powerful and Theoretically Guaranteed Independence Testing on Heterogeneous Federated Clients
1213. ICML 2026Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
1214. ICML 2026Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision
1215. ICML 2026Preference-Calibrated Optimization with Score-Level Distribution Alignment for Text-to-Image Diffusion Model Unlearning
1216. ICML 2026Preference-Enhanced Reinforcement Learning for Pluralistic Image Inpainting
1217. ICML 2026Preference-Modulated Structural Attention for Multi-Objective Combinatorial Optimization
1218. ICML 2026Pressure Reveals Character: Behavioural Alignment Evaluation at Depth
1219. ICML 2026Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
1220. ICML 2026ProMeCD: Unifying Long-Tailed and Noisy Label Learning via White-Box Control
1221. ICML 2026Prototype-guided Bilateral Alignment Multimodal Federated Learning
1222. ICML 2026Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation
1223. ICML 2026PS-PPO : Prefix-Sampling PPO for Critic-Free RLHF
1224. ICML 2026QiMeng-PerceptOS: Semantic-Aware Kernel Optimization for OS-Intensive Workloads via Hardware-Software Alignment
1225. ICML 2026Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis
1226. ICML 2026Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
1227. ICML 2026Rare Event Analysis of Large Language Models
1228. ICML 2026RBCBF: Decoding Time Safety Alignment via Risk Guided Rollback and Barrier Control
1229. ICML 2026Real-Time Aligned Reward Model beyond Semantics
1230. ICML 2026REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
1231. ICML 2026REAR: Test-time Preference Realignment through Reward Decomposition
1232. ICML 2026Reasoning Models Struggle to Control their Chains of Thought
1233. ICML 2026Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
1234. ICML 2026Recontextualization Mitigates Specification Gaming Without Modifying the Specification
1235. ICML 2026RED-HDP-HMM: Observation-Dependent Durations for Bayesian Nonparametric Sequential Models
1236. ICML 2026RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
1237. ICML 2026Regularized Discriminative Alignment for Deep Representations under Label Shift
1238. ICML 2026Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
1239. ICML 2026Reliability-Aware LLM Alignment from Inconsistent Human Feedback
1240. ICML 2026Reliable Confidence Alignment for Generalized Category Discovery
1241. ICML 2026Reliable Neighborhood-Aware Multi-View Outlier Detection
1242. ICML 2026Removing Sandbagging in LLMs by Training with Weak Supervision
1243. ICML 2026Resilient Coresets and Clustering
1244. ICML 2026Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification
1245. ICML 2026Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
1246. ICML 2026Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
1247. ICML 2026Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
1248. ICML 2026Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
1249. ICML 2026Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios
1250. ICML 2026Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective

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.