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 21 of 92

1001. ICML 2026dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
1002. ICML 2026DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
1003. ICML 2026Efficient Bilevel Optimization for CKA-Guided MoE Upcycling
1004. ICML 2026Efficient Distributionally Robust Assortment Optimization in MNL Bandits
1005. ICML 2026Efficient LLM Moderation with Multi-Layer Latent Prototypes
1006. ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
1007. ICML 2026Emergence of Hierarchical Emotion Organization in Large Language Models
1008. ICML 2026Emergent Alignment via Competition
1009. ICML 2026ePC: Fast and Deep Predictive Coding in Digital Simulation
1010. ICML 2026ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
1011. ICML 2026Estimating Tail Risks in Language Model Output Distributions
1012. ICML 2026Evaluating Contextual Illegality: AI Compliance in Corporate Law Scenarios
1013. ICML 2026EVMbench: Evaluating AI Agents on Smart Contract Security
1014. ICML 2026Evolving Interpretable Constitutions for Multi-Agent Coordination
1015. ICML 2026Expectation Alignment of Language Models for Real-World User Expectations
1016. ICML 2026Expert-level Leaf Cell Layout Generation via Preference-Optimized LLM
1017. ICML 2026Explainable Federated Learning via Global–Local Attribution Alignment
1018. ICML 2026Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning
1019. ICML 2026Extracting alignment data in open models
1020. ICML 2026Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
1021. ICML 2026Factored Causal Representation Learning for Robust Reward Modeling in RLHF
1022. ICML 2026FedARC: Anchor-Guided Residual Compensation for Data and Model Heterogeneous Federated Learning
1023. ICML 2026FedCDWA: Decoupled Federated Prototype Distillation with Hierarchical Wasserstein Aggregation
1024. ICML 2026FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model
1025. ICML 2026Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
1026. ICML 2026Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
1027. ICML 2026FedPDG: Prediction Discrepancy–Guided Data Generation for Heterogeneous Federated Learning
1028. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
1029. ICML 2026FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
1030. ICML 2026FIDIA: Function-Informed Sequence Design via Inference-Aligned Policy Optimization
1031. ICML 2026Finding Stationary Points by Comparisons
1032. ICML 2026Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
1033. ICML 2026Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
1034. ICML 2026FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
1035. ICML 2026FLARE-AI: Flaw Reporting for AI
1036. ICML 2026Fleet: Few Shots Lead Effective AI-generated Image Detection
1037. ICML 2026Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
1038. ICML 2026FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
1039. ICML 2026FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
1040. ICML 2026Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
1041. ICML 2026ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models
1042. ICML 2026FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
1043. ICML 2026FormalRx: Rectify and eXamine Semantic Failures in Autoformalization
1044. ICML 2026Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
1045. ICML 2026From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
1046. ICML 2026From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
1047. ICML 2026From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
1048. ICML 2026From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
1049. ICML 2026From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
1050. ICML 2026Frontier Models Can Take Actions at Low Probabilities

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.