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 4 of 28

151. ICLR 2025Accelerating Training with Neuron Interaction and Nowcasting Networks
152. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
153. ICLR 2025Adam-mini: Use Fewer Learning Rates To Gain More
154. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
155. ICLR 2025Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
156. ICLR 2025Adaptive Energy Alignment for Accelerating Test-Time Adaptation
157. ICLR 2025Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
158. ICLR 2025Advancing LLM Reasoning Generalists with Preference Trees
159. ICLR 2025Advantage-Guided Distillation for Preference Alignment in Small Language Models
160. ICLR 2025Adversarial Attacks on Data Attribution
161. ICLR 2025Adversarial Latent Feature Augmentation for Fairness
162. ICLR 2025Adversarial Machine Unlearning
163. ICLR 2025Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
164. ICLR 2025Adversarial Search Engine Optimization for Large Language Models
165. ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
166. ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
167. ICLR 2025AI Sandbagging: Language Models can Strategically Underperform on Evaluations
168. ICLR 2025AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories
169. ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
170. ICLR 2025Aligned LLMs Are Not Aligned Browser Agents
171. ICLR 2025Aligning Language Models with Demonstrated Feedback
172. ICLR 2025Aligning Visual Contrastive learning models via Preference Optimization
173. ICLR 2025ALLaM: Large Language Models for Arabic and English
174. ICLR 2025AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
175. ICLR 2025Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
176. ICLR 2025An Auditing Test to Detect Behavioral Shift in Language Models
177. ICLR 2025An Effective Theory of Bias Amplification
178. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
179. ICLR 2025An Undetectable Watermark for Generative Image Models
180. ICLR 2025Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
181. ICLR 2025As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
182. ICLR 2025Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
183. ICLR 2025Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation
184. ICLR 2025Attention with Markov: A Curious Case of Single-layer Transformers
185. ICLR 2025AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
186. ICLR 2025Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
187. ICLR 2025Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
188. ICLR 2025Backtracking Improves Generation Safety
189. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
190. ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
191. ICLR 2025BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
192. ICLR 2025Balancing Bias in Two-sided Markets for Fair Stable Matchings
193. ICLR 2025Bayesian WeakS-to-Strong from Text Classification to Generation
194. ICLR 2025Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
195. ICLR 2025BingoGuard: LLM Content Moderation Tools with Risk Levels
196. ICLR 2025Black-Box Detection of Language Model Watermarks
197. ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
198. ICLR 2025Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
199. ICLR 2025Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
200. ICLR 2025Bootstrapping Language Models with DPO Implicit Rewards

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.