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 23 of 28

1101. NeurIPS 2025Improved Bounds for Swap Multicalibration and Swap Omniprediction
1102. NeurIPS 2025Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits
1103. NeurIPS 2025Improved Representation Steering for Language Models
1104. NeurIPS 2025Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
1105. NeurIPS 2025Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
1106. NeurIPS 2025Improving Video Generation with Human Feedback
1107. NeurIPS 2025Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion
1108. NeurIPS 2025Incomplete Multi-view Deep Clustering with Data Imputation and Alignment
1109. NeurIPS 2025Inference-time Alignment in Continuous Space
1110. NeurIPS 2025Inference-Time Personalized Alignment with a Few User Preference Queries
1111. NeurIPS 2025Inference-Time Reward Hacking in Large Language Models
1112. NeurIPS 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
1113. NeurIPS 2025Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
1114. NeurIPS 2025InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
1115. NeurIPS 2025Information Retrieval Induced Safety Degradation in AI Agents
1116. NeurIPS 2025Information-Theoretic Reward Decomposition for Generalizable RLHF
1117. NeurIPS 2025Infrequent Exploration in Linear Bandits
1118. NeurIPS 2025Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation
1119. NeurIPS 2025Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval
1120. NeurIPS 2025InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
1121. NeurIPS 2025IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
1122. NeurIPS 2025JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics
1123. NeurIPS 2025JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
1124. NeurIPS 2025Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
1125. NeurIPS 2025KL Penalty Control via Perturbation for Direct Preference Optimization
1126. NeurIPS 2025KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
1127. NeurIPS 2025LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process
1128. NeurIPS 2025Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale
1129. NeurIPS 2025Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
1130. NeurIPS 2025Large language models can learn and generalize steganographic chain-of-thought under process supervision
1131. NeurIPS 2025LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
1132. NeurIPS 2025LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
1133. NeurIPS 2025Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
1134. NeurIPS 2025LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
1135. NeurIPS 2025Learning “Partner-Aware” Collaborators in Multi-Party Collaboration
1136. NeurIPS 2025Learning a Cross-Modal Schrödinger Bridge for Visual Domain Generalization
1137. NeurIPS 2025Learning single index models via harmonic decomposition
1138. NeurIPS 2025Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
1139. NeurIPS 2025Learning to Steer: Input-dependent Steering for Multimodal LLMs
1140. NeurIPS 2025Less is More: Improving LLM Alignment via Preference Data Selection
1141. NeurIPS 2025Let a Neural Network be Your Invariant
1142. NeurIPS 2025Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
1143. NeurIPS 2025Leveraging robust optimization for llm alignment under distribution shifts
1144. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
1145. NeurIPS 2025Lifelong Safety Alignment for Language Models
1146. NeurIPS 2025LLM Safety Alignment is Divergence Estimation in Disguise
1147. NeurIPS 2025LLMs Encode Harmfulness and Refusal Separately
1148. NeurIPS 2025LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
1149. NeurIPS 2025Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
1150. NeurIPS 2025macOSWorld: A Multilingual Interactive Benchmark for GUI Agents

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.