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

1,339 papers, page 9 of 27

401. ICLR 2026Persona Features Control Emergent Misalignment
402. ICLR 2026Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It
403. ICLR 2026PerSpectra: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments
404. ICLR 2026Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
405. ICLR 2026Perturbed Dynamic Time Warping: A Probabilistic Framework and Generalized Variants
406. ICLR 2026PetaGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning
407. ICLR 2026PLAGUE: Plug-and-play Framework for Lifelong Adaptive Generation of Multi-turn Exploits
408. ICLR 2026PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
409. ICLR 2026Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization
410. ICLR 2026PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
411. ICLR 2026PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
412. ICLR 2026PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
413. ICLR 2026Polynomial, trigonometric, and tropical activations
414. ICLR 2026PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
415. ICLR 2026PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
416. ICLR 2026Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
417. ICLR 2026Prediction with Expert Advice under Local Differential Privacy
418. ICLR 2026Preference Leakage: A Contamination Problem in LLM-as-a-judge
419. ICLR 2026Pretrain Value, Not Reward: Decoupled Value Policy Optimization
420. ICLR 2026Pretrain–Test Task Alignment Governs Generalization in In-Context Learning
421. ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
422. ICLR 2026Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
423. ICLR 2026Private Rate-Constrained Optimization with Applications to Fair Learning
424. ICLR 2026PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment
425. ICLR 2026Propaganda AI: An Analysis of Semantic Divergence in Large Language Models
426. ICLR 2026PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
427. ICLR 2026Property-Driven Protein Inverse Folding with Multi-Objective Preference Alignment
428. ICLR 2026ProSafePrune: Projected Safety Pruning for Mitigating Over-Refusal in LLMs
429. ICLR 2026Protection against Source Inference Attacks in Federated Learning
430. ICLR 2026Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
431. ICLR 2026REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
432. ICLR 2026Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
433. ICLR 2026Reasoning Boosts Opinion Alignment in LLMs
434. ICLR 2026RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
435. ICLR 2026RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
436. ICLR 2026Reducing information dependency does not cause training data privacy. Adversarially non-robust features do.
437. ICLR 2026References Improve LLM Alignment in Non-Verifiable Domains
438. ICLR 2026Regulating Internal Evidence Flows for Robust Learning Under Spurious Correlations
439. ICLR 2026Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
440. ICLR 2026Reinforcement Unlearning via Group Relative Policy Optimization
441. ICLR 2026Relationship Alignment for View-aware Multi-view Clustering
442. ICLR 2026RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
443. ICLR 2026Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
444. ICLR 2026Reliable Weak-to-Strong Monitoring of LLM Agents
445. ICLR 2026RepIt: Steering Language Models with Concept-Specific Refusal Vectors
446. ICLR 2026Representation Alignment for Diffusion Transformers without External Components
447. ICLR 2026Representational Alignment Across Model Layers and Brain Regions with Hierarchical Optimal Transport
448. ICLR 2026RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility
449. ICLR 2026Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
450. ICLR 2026Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models

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.