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

1,363 papers, page 17 of 28

801. ICML 2025Position: AI Safety should prioritize the Future of Work
802. ICML 2025Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care
803. ICML 2025Position: Challenges and Future Directions of Data-Centric AI Alignment
804. ICML 2025Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance
805. ICML 2025Position: Editing Large Language Models Poses Serious Safety Risks
806. ICML 2025Position: Humanity Faces Existential Risk from Gradual Disempowerment
807. ICML 2025Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
808. ICML 2025Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
809. ICML 2025Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States
810. ICML 2025Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
811. ICML 2025Position: The Right to AI
812. ICML 2025Position: We Need Responsible, Application-Driven (RAD) AI Research
813. ICML 2025Positional Attention: Expressivity and Learnability of Algorithmic Computation
814. ICML 2025Preference Learning for AI Alignment: a Causal Perspective
815. ICML 2025Preference learning made easy: Everything should be understood through win rate
816. ICML 2025Preference Optimization for Combinatorial Optimization Problems
817. ICML 2025Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
818. ICML 2025Private Federated Learning using Preference-Optimized Synthetic Data
819. ICML 2025Progressively Label Enhancement for Large Language Model Alignment
820. ICML 2025Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
821. ICML 2025ProSec: Fortifying Code LLMs with Proactive Security Alignment
822. ICML 2025Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
823. ICML 2025Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
824. ICML 2025R.I.P.: Better Models by Survival of the Fittest Prompts
825. ICML 2025R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
826. ICML 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
827. ICML 2025RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
828. ICML 2025Reducing Tool Hallucination via Reliability Alignment
829. ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
830. ICML 2025Regularized Langevin Dynamics for Combinatorial Optimization
831. ICML 2025Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss
832. ICML 2025Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
833. ICML 2025Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
834. ICML 2025Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
835. ICML 2025Risk and cross validation in ridge regression with correlated samples
836. ICML 2025RLTHF: Targeted Human Feedback for LLM Alignment
837. ICML 2025ROPO: Robust Preference Optimization for Large Language Models
838. ICML 2025RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
839. ICML 2025RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
840. ICML 2025SAE-V: Interpreting Multimodal Models for Enhanced Alignment
841. ICML 2025Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
842. ICML 2025SAFE: Finding Sparse and Flat Minima to Improve Pruning
843. ICML 2025SafeArena: Evaluating the Safety of Autonomous Web Agents
844. ICML 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signals
845. ICML 2025Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
846. ICML 2025Safety Reasoning with Guidelines
847. ICML 2025Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants
848. ICML 2025Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
849. ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
850. ICML 2025Self-Consistency Preference 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.