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 5 of 28

201. ICLR 2025Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
202. ICLR 2025Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
203. ICLR 2025Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
204. ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
205. ICLR 2025Building Math Agents with Multi-Turn Iterative Preference Learning
206. ICLR 2025Calibrating Expressions of Certainty
207. ICLR 2025Can a Large Language Model be a Gaslighter?
208. ICLR 2025Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
209. ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
210. ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
211. ICLR 2025Can Watermarks be Used to Detect LLM IP Infringement For Free?
212. ICLR 2025Can We Ignore Labels in Out of Distribution Detection?
213. ICLR 2025Capturing the Temporal Dependence of Training Data Influence
214. ICLR 2025Certified Robustness Under Bounded Levenshtein Distance
215. ICLR 2025Certifying Counterfactual Bias in LLMs
216. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
217. ICLR 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
218. ICLR 2025CipherPrune: Efficient and Scalable Private Transformer Inference
219. ICLR 2025Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
220. ICLR 2025Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
221. ICLR 2025CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
222. ICLR 2025Collapsed Language Models Promote Fairness
223. ICLR 2025Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
224. ICLR 2025Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement
225. ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
226. ICLR 2025ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration
227. ICLR 2025Confidence Elicitation: A New Attack Vector for Large Language Models
228. ICLR 2025Conformal Prediction Sets Can Cause Disparate Impact
229. ICLR 2025Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
230. ICLR 2025Conservative Contextual Bandits: Beyond Linear Representations
231. ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
232. ICLR 2025Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis
233. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
234. ICLR 2025Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
235. ICLR 2025Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization
236. ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
237. ICLR 2025Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
238. ICLR 2025Copyright-Protected Language Generation via Adaptive Model Fusion
239. ICLR 2025Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
240. ICLR 2025Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
241. ICLR 2025CREAM: Consistency Regularized Self-Rewarding Language Models
242. ICLR 2025Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
243. ICLR 2025Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
244. ICLR 2025DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
245. ICLR 2025DarkBench: Benchmarking Dark Patterns in Large Language Models
246. ICLR 2025Data Distillation for extrapolative protein design through exact preference optimization
247. ICLR 2025Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning
248. ICLR 2025Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
249. ICLR 2025Dataset Ownership Verification in Contrastive Pre-trained Models
250. ICLR 2025DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

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.