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

551 papers, page 6 of 12

251. ICML 2026Latent Space Robust Optimization of Neural Processes with Aligned Stratified Order-Statistic Loss Reduction
252. ICML 2026Layer-wise Gradient Disentanglement: Decoupling Semantics and Preferences in Direct Preference Optimization
253. ICML 2026Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
254. ICML 2026Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective
255. ICML 2026Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
256. ICML 2026Learning in Structured Stackelberg Games
257. ICML 2026Learning to Remember, Learn, and Forget in Attention-Based Models
258. ICML 2026Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
259. ICML 2026Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
260. ICML 2026Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
261. ICML 2026Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
262. ICML 2026Lightweight and Interpretable Transformer via Unrolling of Mixed Graph Algorithms for Traffic Forecast
263. ICML 2026LILO: Bayesian Optimization with Natural Language Feedback
264. ICML 2026LiMuon: Light and Fast Muon Optimizer for Large Models
265. ICML 2026LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
266. ICML 2026LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent
267. ICML 2026Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
268. ICML 2026Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
269. ICML 2026Local-Minima-Preserving Polynomial Relaxation of Ising Problems
270. ICML 2026Localized, High-resolution Geographic Representations with Slepian Functions
271. ICML 2026Lookahead-GCG: Improving Universal Multi-Model Optimization-Based Jailbreaking Attacks via Stochastic Nesterov Optimization
272. ICML 2026Matroid Algorithms Under Size-Sensitive Independence Oracles
273. ICML 2026MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference
274. ICML 2026Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
275. ICML 2026Measuring Meta-Cultural Competency: A Spectral Framework for LLM Knowledge Structures
276. ICML 2026Mechanistic Anomaly Detection via Functional Attribution
277. ICML 2026Membership Inference Attacks for Unseen Classes
278. ICML 2026MESA: Improving MoE Safety Alignment via Decentralized Expertise
279. ICML 2026Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
280. ICML 2026Mind the Gap: Structure-Aware Consistency in Preference Learning
281. ICML 2026Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
282. ICML 2026MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
283. ICML 2026Mitigating Reward Hacking in LLM-based Recommendation: A Preference Optimization Approach
284. ICML 2026Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
285. ICML 2026Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
286. ICML 2026Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
287. ICML 2026MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance
288. ICML 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge
289. ICML 2026MoDA: Modulation Adapter for Fine-Grained Visual Understanding in Instructional MLLMs
290. ICML 2026Model Fusion via Retrofitting
291. ICML 2026Modeling Attributional Style at Scale: A Dataset and Analysis for Psychological Attribution Assessment and Reframing
292. ICML 2026Modular Pretraining Enables Access Control
293. ICML 2026MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
294. ICML 2026More Capable, Less Cooperative? When LLMs Fail at Zero-Cost Collaboration
295. ICML 2026MRPO: Magnitude-Regularized Policy Optimization via L1 Constraints
296. ICML 2026Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models
297. ICML 2026Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety
298. ICML 2026Multi-Way Representation Alignment
299. ICML 2026MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
300. ICML 2026Multilingual Safety Alignment via Representation-Space Separability

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.