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

1,339 papers, page 20 of 27

951. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
952. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
953. ICLR 2025Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution
954. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
955. ICLR 2025Programming Refusal with Conditional Activation Steering
956. ICLR 2025Prompting Fairness: Integrating Causality to Debias Large Language Models
957. ICLR 2025ProtoSnap: Prototype Alignment For Cuneiform Signs
958. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
959. ICLR 2025Provable weak-to-strong generalization via benign overfitting
960. ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
961. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
962. ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
963. ICLR 2025Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
964. ICLR 2025QA-Calibration of Language Model Confidence Scores
965. ICLR 2025QPM: Discrete Optimization for Globally Interpretable Image Classification
966. ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
967. ICLR 2025Reassessing How to Compare and Improve the Calibration of Machine Learning Models
968. ICLR 2025Reconciling Model Multiplicity for Downstream Decision Making
969. ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
970. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
971. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
972. ICLR 2025Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
973. ICLR 2025Regretful Decisions under Label Noise
974. ICLR 2025Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards
975. ICLR 2025Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems
976. ICLR 2025Remove Symmetries to Control Model Expressivity and Improve Optimization
977. ICLR 2025Representational Similarity via Interpretable Visual Concepts
978. ICLR 2025Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
979. ICLR 2025Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
980. ICLR 2025Rethinking Fair Representation Learning for Performance-Sensitive Tasks
981. ICLR 2025Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
982. ICLR 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
983. ICLR 2025Rethinking Reward Modeling in Preference-based Large Language Model Alignment
984. ICLR 2025Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation
985. ICLR 2025Revisiting Mode Connectivity in Neural Networks with Bezier Surface
986. ICLR 2025Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating
987. ICLR 2025RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
988. ICLR 2025RMB: Comprehensively benchmarking reward models in LLM alignment
989. ICLR 2025Robust System Identification: Finite-sample Guarantees and Connection to Regularization
990. ICLR 2025Robustness Inspired Graph Backdoor Defense
991. ICLR 2025Round and Round We Go! What makes Rotary Positional Encodings useful?
992. ICLR 2025RouteLLM: Learning to Route LLMs from Preference Data
993. ICLR 2025RRM: Robust Reward Model Training Mitigates Reward Hacking
994. ICLR 2025SafeDiffuser: Safe Planning with Diffusion Probabilistic Models
995. ICLR 2025Safety Alignment Should be Made More Than Just a Few Tokens Deep
996. ICLR 2025Safety Layers in Aligned Large Language Models: The Key to LLM Security
997. ICLR 2025SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
998. ICLR 2025Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
999. ICLR 2025SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
1000. ICLR 2025Scalable Extraction of Training Data from Aligned, Production Language Models

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.