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

875 papers, page 15 of 18

701. NeurIPS 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
702. NeurIPS 2024Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
703. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
704. NeurIPS 2024Maia-2: A Unified Model for Human-AI Alignment in Chess
705. NeurIPS 2024MALT Powers Up Adversarial Attacks
706. NeurIPS 2024MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
707. NeurIPS 2024Many-shot Jailbreaking
708. NeurIPS 2024Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
709. NeurIPS 2024Measuring Goal-Directedness
710. NeurIPS 2024Measuring Per-Unit Interpretability at Scale Without Humans
711. NeurIPS 2024MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
712. NeurIPS 2024Mercury: A Code Efficiency Benchmark for Code Large Language Models
713. NeurIPS 2024MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
714. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
715. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
716. NeurIPS 2024Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
717. NeurIPS 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
718. NeurIPS 2024MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
719. NeurIPS 2024MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
720. NeurIPS 2024Multi-turn Reinforcement Learning with Preference Human Feedback
721. NeurIPS 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
722. NeurIPS 2024NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
723. NeurIPS 2024Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
724. NeurIPS 2024Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
725. NeurIPS 2024Noise Contrastive Alignment of Language Models with Explicit Rewards
726. NeurIPS 2024NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
727. NeurIPS 2024On scalable oversight with weak LLMs judging strong LLMs
728. NeurIPS 2024On Softmax Direct Preference Optimization for Recommendation
729. NeurIPS 2024On the Adversarial Robustness of Benjamini Hochberg
730. NeurIPS 2024On the Scalability of Certified Adversarial Robustness with Generated Data
731. NeurIPS 2024On the Use of Anchoring for Training Vision Models
732. NeurIPS 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualization
733. NeurIPS 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
734. NeurIPS 2024Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
735. NeurIPS 2024Optimistic Verifiable Training by Controlling Hardware Nondeterminism
736. NeurIPS 2024Out-Of-Distribution Detection with Diversification (Provably)
737. NeurIPS 2024Panacea: Pareto Alignment via Preference Adaptation for LLMs
738. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
739. NeurIPS 2024PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
740. NeurIPS 2024Perplexity-aware Correction for Robust Alignment with Noisy Preferences
741. NeurIPS 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
742. NeurIPS 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
743. NeurIPS 2024Policy Aggregation
744. NeurIPS 2024Predicting the Performance of Foundation Models via Agreement-on-the-Line
745. NeurIPS 2024Preference Alignment with Flow Matching
746. NeurIPS 2024Preference Learning Algorithms Do Not Learn Preference Rankings
747. NeurIPS 2024Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
748. NeurIPS 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
749. NeurIPS 2024ProgressGym: Alignment with a Millennium of Moral Progress
750. NeurIPS 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach

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.