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

623 papers, page 7 of 13

301. ICLR 2026LatentQA: Teaching LLMs to Decode Activations Into Natural Language
302. ICLR 2026LCA: Local Classifier Alignment for Continual Learning
303. ICLR 2026Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
304. ICLR 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
305. ICLR 2026LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models
306. ICLR 2026Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
307. ICLR 2026Learning Correlated Reward Models: Statistical Barriers and Opportunities
308. ICLR 2026Learning Distributions over Permutations and Rankings with Factorized Representations
309. ICLR 2026Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
310. ICLR 2026Learning Ordinal Probabilistic Reward from Preferences
311. ICLR 2026Learning to summarize user information for personalized reinforcement learning from human feedback
312. ICLR 2026Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment
313. ICLR 2026Learning-Time Encoding Shapes Unlearning in LLMs
314. ICLR 2026Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
315. ICLR 2026LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
316. ICLR 2026LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization
317. ICLR 2026LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion
318. ICLR 2026LLM Fingerprinting via Semantically Conditioned Watermarks
319. ICLR 2026LLM Unlearning with LLM Beliefs
320. ICLR 2026LLMs Can Hide Text in Other Text of the Same Length
321. ICLR 2026LLMS ON TRIAL: Evaluating Judicial Fairness For Large Language Models
322. ICLR 2026Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
323. ICLR 2026Log Probability Tracking of LLM APIs
324. ICLR 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
325. ICLR 2026Low-Pass Filtering Improves Behavioral Alignment of Vision Models
326. ICLR 2026LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
327. ICLR 2026ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
328. ICLR 2026Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
329. ICLR 2026MATRIX: Mask Track Alignment for Interaction-aware Video Generation
330. ICLR 2026MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
331. ICLR 2026Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
332. ICLR 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Models
333. ICLR 2026Membership Privacy Risks of Sharpness Aware Minimization
334. ICLR 2026Memorization Through the Lens of Sample Gradients
335. ICLR 2026MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
336. ICLR 2026Meta-Router: Bridging Gold-standard and Preference-based Evaluations in LLM Routing
337. ICLR 2026MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
338. ICLR 2026Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
339. ICLR 2026Mitigating Mismatch within Reference-based Preference Optimization
340. ICLR 2026Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
341. ICLR 2026Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
342. ICLR 2026Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization
343. ICLR 2026MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference
344. ICLR 2026MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
345. ICLR 2026Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
346. ICLR 2026Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
347. ICLR 2026Modality-free Graph In-context Alignment
348. ICLR 2026Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
349. ICLR 2026MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
350. ICLR 2026Monitoring Decomposition Attacks with Lightweight Sequential Monitors

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.