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 82 of 92

4051. NeurIPS 2024Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
4052. NeurIPS 2024SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
4053. NeurIPS 2024SimPO: Simple Preference Optimization with a Reference-Free Reward
4054. NeurIPS 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
4055. NeurIPS 2024Soft-Label Integration for Robust Toxicity Classification
4056. NeurIPS 2024Spectral Editing of Activations for Large Language Model Alignment
4057. NeurIPS 2024SpeechAlign: Aligning Speech Generation to Human Preferences
4058. NeurIPS 2024SSDM: Scalable Speech Dysfluency Modeling
4059. NeurIPS 2024Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
4060. NeurIPS 2024Stepwise Alignment for Constrained Language Model Policy Optimization
4061. NeurIPS 2024Stress-Testing Capability Elicitation With Password-Locked Models
4062. NeurIPS 2024Studying How to Efficiently and Effectively Guide Models with Explanations - A Reproducibility Study
4063. NeurIPS 2024T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
4064. NeurIPS 2024Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
4065. NeurIPS 2024TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
4066. NeurIPS 2024Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
4067. NeurIPS 2024Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
4068. NeurIPS 2024TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
4069. NeurIPS 2024The Art of Saying No: Contextual Noncompliance in Language Models
4070. NeurIPS 2024The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
4071. NeurIPS 2024The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
4072. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
4073. NeurIPS 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
4074. NeurIPS 2024TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
4075. NeurIPS 2024TopoFR: A Closer Look at Topology Alignment on Face Recognition
4076. NeurIPS 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
4077. NeurIPS 2024Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
4078. NeurIPS 2024Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
4079. NeurIPS 2024Transfer Q-star : Principled Decoding for LLM Alignment
4080. NeurIPS 2024Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
4081. NeurIPS 2024Transferable Adversarial Attacks on SAM and Its Downstream Models
4082. NeurIPS 2024Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
4083. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
4084. NeurIPS 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
4085. NeurIPS 2024Truth is Universal: Robust Detection of Lies in LLMs
4086. NeurIPS 2024UltraMedical: Building Specialized Generalists in Biomedicine
4087. NeurIPS 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vector
4088. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
4089. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
4090. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
4091. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
4092. NeurIPS 2024Unified Lexical Representation for Interpretable Visual-Language Alignment
4093. NeurIPS 2024UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
4094. NeurIPS 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
4095. NeurIPS 2024Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
4096. NeurIPS 2024UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
4097. NeurIPS 2024Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
4098. NeurIPS 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
4099. NeurIPS 2024Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
4100. NeurIPS 2024Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning 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.