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 4 of 24

151. ICML 2026DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
152. ICML 2026Efficient Bilevel Optimization for CKA-Guided MoE Upcycling
153. ICML 2026Efficient Distributionally Robust Assortment Optimization in MNL Bandits
154. ICML 2026Efficient LLM Moderation with Multi-Layer Latent Prototypes
155. ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
156. ICML 2026Emergence of Hierarchical Emotion Organization in Large Language Models
157. ICML 2026Emergent Alignment via Competition
158. ICML 2026ePC: Fast and Deep Predictive Coding in Digital Simulation
159. ICML 2026ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
160. ICML 2026Estimating Tail Risks in Language Model Output Distributions
161. ICML 2026Evaluating Contextual Illegality: AI Compliance in Corporate Law Scenarios
162. ICML 2026EVMbench: Evaluating AI Agents on Smart Contract Security
163. ICML 2026Evolving Interpretable Constitutions for Multi-Agent Coordination
164. ICML 2026Expectation Alignment of Language Models for Real-World User Expectations
165. ICML 2026Expert-level Leaf Cell Layout Generation via Preference-Optimized LLM
166. ICML 2026Explainable Federated Learning via Global–Local Attribution Alignment
167. ICML 2026Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning
168. ICML 2026Extracting alignment data in open models
169. ICML 2026Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
170. ICML 2026Factored Causal Representation Learning for Robust Reward Modeling in RLHF
171. ICML 2026FedARC: Anchor-Guided Residual Compensation for Data and Model Heterogeneous Federated Learning
172. ICML 2026FedCDWA: Decoupled Federated Prototype Distillation with Hierarchical Wasserstein Aggregation
173. ICML 2026FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model
174. ICML 2026Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
175. ICML 2026Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
176. ICML 2026FedPDG: Prediction Discrepancy–Guided Data Generation for Heterogeneous Federated Learning
177. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
178. ICML 2026FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
179. ICML 2026FIDIA: Function-Informed Sequence Design via Inference-Aligned Policy Optimization
180. ICML 2026Finding Stationary Points by Comparisons
181. ICML 2026Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
182. ICML 2026Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
183. ICML 2026FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
184. ICML 2026FLARE-AI: Flaw Reporting for AI
185. ICML 2026Fleet: Few Shots Lead Effective AI-generated Image Detection
186. ICML 2026Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
187. ICML 2026FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
188. ICML 2026FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
189. ICML 2026Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
190. ICML 2026ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models
191. ICML 2026FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
192. ICML 2026FormalRx: Rectify and eXamine Semantic Failures in Autoformalization
193. ICML 2026Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
194. ICML 2026From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
195. ICML 2026From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
196. ICML 2026From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
197. ICML 2026From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
198. ICML 2026From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
199. ICML 2026Frontier Models Can Take Actions at Low Probabilities
200. ICML 2026Furina: Fragmented Uncertainty-Driven Refusal Instability Attack

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.