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 12 of 92

551. ICLR 2026Log Probability Tracking of LLM APIs
552. ICLR 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
553. ICLR 2026Low-Pass Filtering Improves Behavioral Alignment of Vision Models
554. ICLR 2026LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
555. ICLR 2026ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
556. ICLR 2026Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
557. ICLR 2026MATRIX: Mask Track Alignment for Interaction-aware Video Generation
558. ICLR 2026MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
559. ICLR 2026Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
560. ICLR 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Models
561. ICLR 2026Membership Privacy Risks of Sharpness Aware Minimization
562. ICLR 2026Memorization Through the Lens of Sample Gradients
563. ICLR 2026MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
564. ICLR 2026Meta-Router: Bridging Gold-standard and Preference-based Evaluations in LLM Routing
565. ICLR 2026MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
566. ICLR 2026Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
567. ICLR 2026Mitigating Mismatch within Reference-based Preference Optimization
568. ICLR 2026Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
569. ICLR 2026Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
570. ICLR 2026Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization
571. ICLR 2026MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference
572. ICLR 2026MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
573. ICLR 2026Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
574. ICLR 2026Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
575. ICLR 2026Modality-free Graph In-context Alignment
576. ICLR 2026Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
577. ICLR 2026MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
578. ICLR 2026Monitoring Decomposition Attacks with Lightweight Sequential Monitors
579. ICLR 2026More Than What Was Chosen: LLM-based Explainable Recommendation Beyond Noisy User Preferences
580. ICLR 2026MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
581. ICLR 2026mR3: Multilingual Rubric-Agnostic Reward Reasoning Models
582. ICLR 2026Multi-Feature Quantized Self-Attention for Fair Large Language Models
583. ICLR 2026Multi-objective Large Language Model Alignment with Hierarchical Experts
584. ICLR 2026Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
585. ICLR 2026Multiplayer Nash Preference Optimization
586. ICLR 2026Narrow Finetuning Leaves Clearly Readable Traces in the Activation Differences
587. ICLR 2026Nasty Adversarial Training: A Probability Sparsity Perspective for Robustness Enhancement
588. ICLR 2026NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection
589. ICLR 2026Neologism Learning for Controllability and Self-Verbalization
590. ICLR 2026NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
591. ICLR 2026No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
592. ICLR 2026Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
593. ICLR 2026Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds
594. ICLR 2026NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context
595. ICLR 2026Obfuscated Activations Bypass LLM Latent-Space Defenses
596. ICLR 2026Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
597. ICLR 2026OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
598. ICLR 2026OFMU: OPTIMIZATION-DRIVEN FRAMEWORK FOR MACHINE UNLEARNING
599. ICLR 2026Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
600. ICLR 2026OmniPortrait: Fine-Grained Personalized Portrait Synthesis via Pivotal Optimization

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.