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

4,558 papers, page 13 of 92

601. ICLR 2026On Fairness of Task Arithmetic: The Role of Task Vectors
602. ICLR 2026On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
603. ICLR 2026On the Alignment Between Supervised and Self-Supervised Contrastive Learning
604. ICLR 2026On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
605. ICLR 2026On the Interaction of Compressibility and Adversarial Robustness
606. ICLR 2026Only Brains Align with Brains: Cross-Region Patterns Expose Limits of Normative Models
607. ICLR 2026OpenAgentSafety: A Comprehensive Framework For Evaluating Real-World AI Agent Safety
608. ICLR 2026Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
609. ICLR 2026OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
610. ICLR 2026Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
611. ICLR 2026Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
612. ICLR 2026Optimizing Agent Planning for Security and Autonomy
613. ICLR 2026Optimizing Canaries for Privacy Auditing with Metagradient Descent
614. ICLR 2026Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement
615. ICLR 2026ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation
616. ICLR 2026OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
617. ICLR 2026Out of the Shadows: Exploring a Latent Space for Neural Network Verification
618. ICLR 2026Output Supervision Can Obfuscate the Chain of Thought
619. ICLR 2026Oversmoothing, "Oversquashing'', Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
620. ICLR 2026P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
621. ICLR 2026P$^2$-DPO:Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
622. ICLR 2026PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
623. ICLR 2026PALC: Preference Alignment via Logit Calibration
624. ICLR 2026PAMDP: Interact to Persona Alignment via a Partially Observable Markov Decision Process
625. ICLR 2026Parameterized Hardness of Zonotope Containment and Neural Network Verification
626. ICLR 2026PCPO: Proportionate Credit Policy Optimization for Preference Alignment of Image Generation Models
627. ICLR 2026PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
628. ICLR 2026Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
629. ICLR 2026Persona Features Control Emergent Misalignment
630. ICLR 2026Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It
631. ICLR 2026PerSpectra: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments
632. ICLR 2026Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
633. ICLR 2026Perturbed Dynamic Time Warping: A Probabilistic Framework and Generalized Variants
634. ICLR 2026PetaGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning
635. ICLR 2026PLAGUE: Plug-and-play Framework for Lifelong Adaptive Generation of Multi-turn Exploits
636. ICLR 2026PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
637. ICLR 2026Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization
638. ICLR 2026PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
639. ICLR 2026PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
640. ICLR 2026PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
641. ICLR 2026Polynomial, trigonometric, and tropical activations
642. ICLR 2026PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
643. ICLR 2026PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
644. ICLR 2026Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
645. ICLR 2026Prediction with Expert Advice under Local Differential Privacy
646. ICLR 2026Preference Leakage: A Contamination Problem in LLM-as-a-judge
647. ICLR 2026Pretrain Value, Not Reward: Decoupled Value Policy Optimization
648. ICLR 2026Pretrain–Test Task Alignment Governs Generalization in In-Context Learning
649. ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
650. ICLR 2026Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding

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.