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

1,363 papers, page 6 of 28

251. ICLR 2025Deep Kernel Relative Test for Machine-generated Text Detection
252. ICLR 2025Democratic Training Against Universal Adversarial Perturbations
253. ICLR 2025Detecting Backdoor Samples in Contrastive Language Image Pretraining
254. ICLR 2025Differentiable Optimization of Similarity Scores Between Models and Brains
255. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending
256. ICLR 2025Differentially private optimization for non-decomposable objective functions
257. ICLR 2025Differentially Private Steering for Large Language Model Alignment
258. ICLR 2025Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models
259. ICLR 2025DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
260. ICLR 2025Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training Demonstrations
261. ICLR 2025DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
262. ICLR 2025Dissecting Adversarial Robustness of Multimodal LM Agents
263. ICLR 2025Diverse Preference Learning for Capabilities and Alignment
264. ICLR 2025Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
265. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
266. ICLR 2025Does Refusal Training in LLMs Generalize to the Past Tense?
267. ICLR 2025Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
268. ICLR 2025DSPO: Direct Score Preference Optimization for Diffusion Model Alignment
269. ICLR 2025Durable Quantization Conditioned Misalignment Attack on Large Language Models
270. ICLR 2025DynAlign: Unsupervised Dynamic Taxonomy Alignment for Cross-Domain Segmentation
271. ICLR 2025Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense
272. ICLR 2025DynFrs: An Efficient Framework for Machine Unlearning in Random Forest
273. ICLR 2025Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
274. ICLR 2025Effective Interplay between Sparsity and Quantization: From Theory to Practice
275. ICLR 2025Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based Coresets
276. ICLR 2025Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
277. ICLR 2025EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
278. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
279. ICLR 2025EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment
280. ICLR 2025Encryption-Friendly LLM Architecture
281. ICLR 2025Endless Jailbreaks with Bijection Learning
282. ICLR 2025Endowing Visual Reprogramming with Adversarial Robustness
283. ICLR 2025Energy-based Backdoor Defense Against Federated Graph Learning
284. ICLR 2025Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded Boundary
285. ICLR 2025Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies
286. ICLR 2025Enhancing Learning with Label Differential Privacy by Vector Approximation
287. ICLR 2025Enhancing Robust Fairness via Confusional Spectral Regularization
288. ICLR 2025Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer
289. ICLR 2025ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
290. ICLR 2025EvA: Erasing Spurious Correlations with Activations
291. ICLR 2025Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study
292. ICLR 2025Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes
293. ICLR 2025Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-Norm
294. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
295. ICLR 2025Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness
296. ICLR 2025Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
297. ICLR 2025Fair Clustering in the Sliding Window Model
298. ICLR 2025FairDen: Fair Density-Based Clustering
299. ICLR 2025FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
300. ICLR 2025Fantastic Copyrighted Beasts and How (Not) to Generate Them

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.