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 19 of 24

901. ICML 2024Deep Networks Always Grok and Here is Why
902. ICML 2024Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
903. ICML 2024Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
904. ICML 2024Dense Reward for Free in Reinforcement Learning from Human Feedback
905. ICML 2024Detecting and Identifying Selection Structure in Sequential Data
906. ICML 2024Differentiability and Optimization of Multiparameter Persistent Homology
907. ICML 2024Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
908. ICML 2024Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery
909. ICML 2024Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification
910. ICML 2024Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset
911. ICML 2024Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
912. ICML 2024EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism
913. ICML 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
914. ICML 2024Emergent Equivariance in Deep Ensembles
915. ICML 2024Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
916. ICML 2024Enhancing Implicit Shape Generators Using Topological Regularizations
917. ICML 2024Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models
918. ICML 2024Equivariant Deep Weight Space Alignment
919. ICML 2024Equivariant Frames and the Impossibility of Continuous Canonicalization
920. ICML 2024Estimating Barycenters of Distributions with Neural Optimal Transport
921. ICML 2024Estimating Canopy Height at Scale
922. ICML 2024Expand-and-Cluster: Parameter Recovery of Neural Networks
923. ICML 2024Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
924. ICML 2024Exploring the LLM Journey from Cognition to Expression with Linear Representations
925. ICML 2024Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
926. ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
927. ICML 2024FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
928. ICML 2024FESSNC: Fast Exponentially Stable and Safe Neural Controller
929. ICML 2024Flextron: Many-in-One Flexible Large Language Model
930. ICML 2024From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
931. ICML 2024Fundamental Limitations of Alignment in Large Language Models
932. ICML 2024Generalized Preference Optimization: A Unified Approach to Offline Alignment
933. ICML 2024GNNs Also Deserve Editing, and They Need It More Than Once
934. ICML 2024Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
935. ICML 2024GRATH: Gradual Self-Truthifying for Large Language Models
936. ICML 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
937. ICML 2024Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
938. ICML 2024High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference Cost
939. ICML 2024How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
940. ICML 2024How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
941. ICML 2024How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
942. ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
943. ICML 2024IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
944. ICML 2024Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
945. ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
946. ICML 2024Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
947. ICML 2024Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
948. ICML 2024In-Context Language Learning: Architectures and Algorithms
949. ICML 2024In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
950. ICML 2024InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning

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.