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

1,198 papers, page 16 of 24

751. ICML 2025Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
752. ICML 2025Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States
753. ICML 2025Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
754. ICML 2025Position: The Right to AI
755. ICML 2025Position: We Need Responsible, Application-Driven (RAD) AI Research
756. ICML 2025Positional Attention: Expressivity and Learnability of Algorithmic Computation
757. ICML 2025Preference Learning for AI Alignment: a Causal Perspective
758. ICML 2025Preference learning made easy: Everything should be understood through win rate
759. ICML 2025Preference Optimization for Combinatorial Optimization Problems
760. ICML 2025Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
761. ICML 2025Private Federated Learning using Preference-Optimized Synthetic Data
762. ICML 2025Progressively Label Enhancement for Large Language Model Alignment
763. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
764. ICML 2025ProSec: Fortifying Code LLMs with Proactive Security Alignment
765. ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
766. ICML 2025Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
767. ICML 2025R.I.P.: Better Models by Survival of the Fittest Prompts
768. ICML 2025R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
769. ICML 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
770. ICML 2025RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
771. ICML 2025Reducing Tool Hallucination via Reliability Alignment
772. ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
773. ICML 2025Regularized Langevin Dynamics for Combinatorial Optimization
774. ICML 2025Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss
775. ICML 2025Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
776. ICML 2025Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
777. ICML 2025Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
778. ICML 2025Risk and cross validation in ridge regression with correlated samples
779. ICML 2025RLTHF: Targeted Human Feedback for LLM Alignment
780. ICML 2025ROPO: Robust Preference Optimization for Large Language Models
781. ICML 2025RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
782. ICML 2025RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
783. ICML 2025SAE-V: Interpreting Multimodal Models for Enhanced Alignment
784. ICML 2025Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
785. ICML 2025SAFE: Finding Sparse and Flat Minima to Improve Pruning
786. ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
787. ICML 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signals
788. ICML 2025Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
789. ICML 2025Safety Reasoning with Guidelines
790. ICML 2025Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants
791. ICML 2025Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
792. ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
793. ICML 2025Self-Consistency Preference Optimization
794. ICML 2025Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
795. ICML 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
796. ICML 2025SEMU: Singular Value Decomposition for Efficient Machine Unlearning
797. ICML 2025SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
798. ICML 2025SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
799. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
800. ICML 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences

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.