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 10 of 28

451. ICLR 2025Persistent Pre-training Poisoning of LLMs
452. ICLR 2025Personality Alignment of Large Language Models
453. ICLR 2025PersonalLLM: Tailoring LLMs to Individual Preferences
454. ICLR 2025PFGuard: A Generative Framework with Privacy and Fairness Safeguards
455. ICLR 2025PiCO: Peer Review in LLMs based on Consistency Optimization
456. ICLR 2025Plastic Learning with Deep Fourier Features
457. ICLR 2025Policy Design in Long-run Welfare Dynamics
458. ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias
459. ICLR 2025Preference Diffusion for Recommendation
460. ICLR 2025Preference Optimization for Reasoning with Pseudo Feedback
461. ICLR 2025Privacy Auditing of Large Language Models
462. ICLR 2025Privately Counting Partially Ordered Data
463. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
464. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
465. ICLR 2025Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution
466. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
467. ICLR 2025Programming Refusal with Conditional Activation Steering
468. ICLR 2025Prompting Fairness: Integrating Causality to Debias Large Language Models
469. ICLR 2025ProtoSnap: Prototype Alignment For Cuneiform Signs
470. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
471. ICLR 2025Provable weak-to-strong generalization via benign overfitting
472. ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
473. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
474. ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
475. ICLR 2025Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
476. ICLR 2025QA-Calibration of Language Model Confidence Scores
477. ICLR 2025QPM: Discrete Optimization for Globally Interpretable Image Classification
478. ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
479. ICLR 2025Reassessing How to Compare and Improve the Calibration of Machine Learning Models
480. ICLR 2025Reconciling Model Multiplicity for Downstream Decision Making
481. ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
482. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
483. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
484. ICLR 2025Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
485. ICLR 2025Regretful Decisions under Label Noise
486. ICLR 2025Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards
487. ICLR 2025Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems
488. ICLR 2025Remove Symmetries to Control Model Expressivity and Improve Optimization
489. ICLR 2025Representational Similarity via Interpretable Visual Concepts
490. ICLR 2025Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
491. ICLR 2025Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
492. ICLR 2025Rethinking Fair Representation Learning for Performance-Sensitive Tasks
493. ICLR 2025Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
494. ICLR 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
495. ICLR 2025Rethinking Reward Modeling in Preference-based Large Language Model Alignment
496. ICLR 2025Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation
497. ICLR 2025Revisiting Mode Connectivity in Neural Networks with Bezier Surface
498. ICLR 2025Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating
499. ICLR 2025RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
500. ICLR 2025RMB: Comprehensively benchmarking reward models in LLM 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.