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 22 of 92

1051. ICML 2026Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
1052. ICML 2026FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification
1053. ICML 2026GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
1054. ICML 2026Generalizable and Composable Multi-Model Embedding Translation
1055. ICML 2026GeoAlign: Geometric Rollout Curation for Robust LLM Reinforcement Learning
1056. ICML 2026GeoDM: Geometry-aware Distribution Matching for Dataset Distillation
1057. ICML 2026Geometric Conformal Prediction with Spatial Ranks and Multivariate Quantiles
1058. ICML 2026Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning
1059. ICML 2026Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models
1060. ICML 2026GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
1061. ICML 2026GLAD: Bidirectional Structure-Attribute Alignment via Latent Graph Diffusion Models
1062. ICML 2026Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization
1063. ICML 2026Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
1064. ICML 2026Gradient Testing and Estimation by Comparisons
1065. ICML 2026Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings
1066. ICML 2026Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
1067. ICML 2026Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare Estimation
1068. ICML 2026Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance
1069. ICML 2026Gromov-Wasserstein at Scale, Beyond Squared Norms
1070. ICML 2026Guaranteed Optimal Compositional Explanations for Neurons
1071. ICML 2026Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
1072. ICML 2026Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
1073. ICML 2026Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
1074. ICML 2026Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
1075. ICML 2026High-Fidelity ANN-to-SNN Conversion via Closed-Loop CKA Distillation
1076. ICML 2026HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
1077. ICML 2026How High is ‘High’? Rethinking the Roles of Dimensionality in Topological Data Analysis and Manifold Learning
1078. ICML 2026How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
1079. ICML 2026How RLHF Amplifies Sycophancy
1080. ICML 2026How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs
1081. ICML 2026HumanLM: Simulating Users with State Alignment Beats Response Imitation
1082. ICML 2026IBMA: Information Bottleneck-Based Multimodal Alignment
1083. ICML 2026Identifying and Mitigating Errors in Gradient Aggregation of Distributed Data Parallel Training
1084. ICML 2026Implicit Preference Alignment for Human Image Animation
1085. ICML 2026Implicit Safety Alignment from Crowd Preferences
1086. ICML 2026Improved Bounds for Private and Robust Alignment
1087. ICML 2026In-Context Universal Approximation, Compositional Generalization, and Algorithm Emulation
1088. ICML 2026In-Training Defenses Against Emergent Misalignment in Language Models
1089. ICML 2026Incorporating Importance Weighting in Optimal Transport Based Domain Alignment
1090. ICML 2026Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO
1091. ICML 2026Inference-time Alignment with Rewards in Besov Spaces: Provable Advantages of Feature Learning and Multi-Step Policy Updates
1092. ICML 2026Instance-Specific Approximation Ratios for Correlation Clustering and Max-Cut
1093. ICML 2026Introspection Adapters: Training LLMs to Report Their Learned Behaviors
1094. ICML 2026IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
1095. ICML 2026IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models
1096. ICML 2026It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
1097. ICML 2026ITSPACE: Monotone Gaussian Optimal Transport Updates
1098. ICML 2026IVQ: Structured and Lightweight Vector Quantization via Binary Hierarchical Composition Inspired by $\textit{IChing}$
1099. ICML 2026Jailbreaking Vision-Language Models Through the Visual Modality
1100. ICML 2026Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation

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.