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 61 of 92

3001. NeurIPS 2025Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval
3002. NeurIPS 2025InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
3003. NeurIPS 2025IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
3004. NeurIPS 2025JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics
3005. NeurIPS 2025JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
3006. NeurIPS 2025Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
3007. NeurIPS 2025KL Penalty Control via Perturbation for Direct Preference Optimization
3008. NeurIPS 2025KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
3009. NeurIPS 2025LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process
3010. NeurIPS 2025Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale
3011. NeurIPS 2025Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
3012. NeurIPS 2025Large language models can learn and generalize steganographic chain-of-thought under process supervision
3013. NeurIPS 2025LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
3014. NeurIPS 2025LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
3015. NeurIPS 2025Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
3016. NeurIPS 2025LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
3017. NeurIPS 2025Learning “Partner-Aware” Collaborators in Multi-Party Collaboration
3018. NeurIPS 2025Learning a Cross-Modal Schrödinger Bridge for Visual Domain Generalization
3019. NeurIPS 2025Learning single index models via harmonic decomposition
3020. NeurIPS 2025Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
3021. NeurIPS 2025Learning to Steer: Input-dependent Steering for Multimodal LLMs
3022. NeurIPS 2025Less is More: Improving LLM Alignment via Preference Data Selection
3023. NeurIPS 2025Let a Neural Network be Your Invariant
3024. NeurIPS 2025Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
3025. NeurIPS 2025Leveraging robust optimization for llm alignment under distribution shifts
3026. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
3027. NeurIPS 2025Lifelong Safety Alignment for Language Models
3028. NeurIPS 2025LLM Safety Alignment is Divergence Estimation in Disguise
3029. NeurIPS 2025LLMs Encode Harmfulness and Refusal Separately
3030. NeurIPS 2025LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
3031. NeurIPS 2025Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
3032. NeurIPS 2025macOSWorld: A Multilingual Interactive Benchmark for GUI Agents
3033. NeurIPS 2025Many LLMs Are More Utilitarian Than One
3034. NeurIPS 2025Matchings Under Biased and Correlated Evaluations
3035. NeurIPS 2025Measuring and Guiding Monosemanticity
3036. NeurIPS 2025Mechanism Design for LLM Fine-tuning with Multiple Reward Models
3037. NeurIPS 2025Median Selection with Noisy and Structural Information
3038. NeurIPS 2025Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
3039. NeurIPS 2025Meta-Learning Objectives for Preference Optimization
3040. NeurIPS 2025MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
3041. NeurIPS 2025Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications
3042. NeurIPS 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
3043. NeurIPS 2025Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
3044. NeurIPS 2025Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models
3045. NeurIPS 2025Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
3046. NeurIPS 2025MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference
3047. NeurIPS 2025Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning
3048. NeurIPS 2025Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One
3049. NeurIPS 2025Multi-step Visual Reasoning with Visual Tokens Scaling and Verification
3050. NeurIPS 2025Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment

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.