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 63 of 92

3101. NeurIPS 2025Prior Forgetting and In-Context Overfitting
3102. NeurIPS 2025Probabilistic Stability Guarantees for Feature Attributions
3103. NeurIPS 2025Probabilistic Token Alignment for Large Language Model Fusion
3104. NeurIPS 2025Prohibiting Generative AI in any Form of Weapon Control
3105. NeurIPS 2025Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a Restorer
3106. NeurIPS 2025Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
3107. NeurIPS 2025Protein Inverse Folding From Structure Feedback
3108. NeurIPS 2025Provably Efficient Online RLHF with One-Pass Reward Modeling
3109. NeurIPS 2025Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO
3110. NeurIPS 2025PurpCode: Reasoning for Safer Code Generation
3111. NeurIPS 2025Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers
3112. NeurIPS 2025Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
3113. NeurIPS 2025Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
3114. NeurIPS 2025Real-DRL: Teach and Learn in Reality
3115. NeurIPS 2025Reasoning as an Adaptive Defense for Safety
3116. NeurIPS 2025Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
3117. NeurIPS 2025Reconstruction and Secrecy under Approximate Distance Queries
3118. NeurIPS 2025Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
3119. NeurIPS 2025Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
3120. NeurIPS 2025Refusal Direction is Universal Across Safety-Aligned Languages
3121. NeurIPS 2025Reinforcement Learning with Backtracking Feedback
3122. NeurIPS 2025Reliably detecting model failures in deployment without labels
3123. NeurIPS 2025RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models
3124. NeurIPS 2025ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
3125. NeurIPS 2025RePO: Understanding Preference Learning Through ReLU-Based Optimization
3126. NeurIPS 2025Residual Stream Analysis of Overfitting And Structural Disruptions
3127. NeurIPS 2025ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
3128. NeurIPS 2025RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
3129. NeurIPS 2025Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
3130. NeurIPS 2025Risk-aware Direct Preference Optimization under Nested Risk Measure
3131. NeurIPS 2025Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding
3132. NeurIPS 2025Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
3133. NeurIPS 2025Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
3134. NeurIPS 2025RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
3135. NeurIPS 2025RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
3136. NeurIPS 2025SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
3137. NeurIPS 2025Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
3138. NeurIPS 2025Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
3139. NeurIPS 2025SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
3140. NeurIPS 2025SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
3141. NeurIPS 2025Safety Depth in Large Language Models: A Markov Chain Perspective
3142. NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
3143. NeurIPS 2025SafeVid: Toward Safety Aligned Video Large Multimodal Models
3144. NeurIPS 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
3145. NeurIPS 2025SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
3146. NeurIPS 2025SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
3147. NeurIPS 2025Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity
3148. NeurIPS 2025Scalable Valuation of Human Feedback through Provably Robust Model Alignment
3149. NeurIPS 2025Scaling and context steer LLMs along the same computational path as the human brain
3150. NeurIPS 2025Scaling Laws For Scalable Oversight

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.