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 11 of 28

501. ICLR 2025Robust System Identification: Finite-sample Guarantees and Connection to Regularization
502. ICLR 2025Robustness Inspired Graph Backdoor Defense
503. ICLR 2025Round and Round We Go! What makes Rotary Positional Encodings useful?
504. ICLR 2025RouteLLM: Learning to Route LLMs from Preference Data
505. ICLR 2025RRM: Robust Reward Model Training Mitigates Reward Hacking
506. ICLR 2025SafeDiffuser: Safe Planning with Diffusion Probabilistic Models
507. ICLR 2025Safety Alignment Should be Made More Than Just a Few Tokens Deep
508. ICLR 2025Safety Layers in Aligned Large Language Models: The Key to LLM Security
509. ICLR 2025SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
510. ICLR 2025Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
511. ICLR 2025SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
512. ICLR 2025Scalable Extraction of Training Data from Aligned, Production Language Models
513. ICLR 2025Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML
514. ICLR 2025SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
515. ICLR 2025SEBRA : Debiasing through Self-Guided Bias Ranking
516. ICLR 2025SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography
517. ICLR 2025Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models
518. ICLR 2025Selective Unlearning via Representation Erasure Using Domain Adversarial Training
519. ICLR 2025Self-Boosting Large Language Models with Synthetic Preference Data
520. ICLR 2025SELF-EVOLVED REWARD LEARNING FOR LLMS
521. ICLR 2025Self-Improvement in Language Models: The Sharpening Mechanism
522. ICLR 2025Self-Improving Robust Preference Optimization
523. ICLR 2025Self-Play Preference Optimization for Language Model Alignment
524. ICLR 2025Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
525. ICLR 2025Sensitivity Verification for Additive Decision Tree Ensembles
526. ICLR 2025SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins
527. ICLR 2025Severing Spurious Correlations with Data Pruning
528. ICLR 2025Shape as Line Segments: Accurate and Flexible Implicit Surface Representation
529. ICLR 2025Shh, don't say that! Domain Certification in LLMs
530. ICLR 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
531. ICLR 2025Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype Construction
532. ICLR 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translation
533. ICLR 2025SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
534. ICLR 2025Sparse components distinguish visual pathways & their alignment to neural networks
535. ICLR 2025Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
536. ICLR 2025Spurious Forgetting in Continual Learning of Language Models
537. ICLR 2025Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
538. ICLR 2025Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
539. ICLR 2025Strategic Classification With Externalities
540. ICLR 2025Strong Preferences Affect the Robustness of Preference Models and Value Alignment
541. ICLR 2025Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
542. ICLR 2025Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
543. ICLR 2025SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
544. ICLR 2025Support is All You Need for Certified VAE Training
545. ICLR 2025Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
546. ICLR 2025Tailoring Mixup to Data for Calibration
547. ICLR 2025Taming Overconfidence in LLMs: Reward Calibration in RLHF
548. ICLR 2025Tamper-Resistant Safeguards for Open-Weight LLMs
549. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
550. ICLR 2025Test-time Adaptation for Regression by Subspace 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.