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

1,882 papers, page 11 of 38

501. ICLR 2026ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
502. ICLR 2026Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment
503. ICLR 2026In-Context Watermarks for Large Language Models
504. ICLR 2026Incentive-Aligned LLM Summaries
505. ICLR 2026Inconsistency Biases in Dynamic Data Pruning
506. ICLR 2026Inference-Time Personalized Safety Control via Paired Difference-in-Means Intervention
507. ICLR 2026INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
508. ICLR 2026Inoculation Prompting: Eliciting traits from LLMs during training can reduce trait expression at test-time
509. ICLR 2026INTIMA: A Benchmark for Human-AI Companionship Behavior
510. ICLR 2026Intrinsic Explanation of Random Subspace Method for Enhanced Security Applications
511. ICLR 2026Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
512. ICLR 2026Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
513. ICLR 2026Is On-Policy Data always the Best Choice for Direct Preference Optimization-Based LM Alignment?
514. ICLR 2026Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
515. ICLR 2026It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
516. ICLR 2026Jailbreak Transferability Emerges from Shared Representations
517. ICLR 2026Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
518. ICLR 2026Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
519. ICLR 2026JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be Unsafe
520. ICLR 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
521. ICLR 2026JULI: Jailbreak Large Language Models by Self-Introspection
522. ICLR 2026Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
523. ICLR 2026K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
524. ICLR 2026Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization
525. ICLR 2026Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models
526. ICLR 2026Label Smoothing Improves Machine Unlearning
527. ICLR 2026Large Language Model Compression with Global Rank and Sparsity Optimization
528. ICLR 2026Latent Speech-Text Transformer
529. ICLR 2026LatentQA: Teaching LLMs to Decode Activations Into Natural Language
530. ICLR 2026LCA: Local Classifier Alignment for Continual Learning
531. ICLR 2026Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
532. ICLR 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
533. ICLR 2026LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models
534. ICLR 2026Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
535. ICLR 2026Learning Correlated Reward Models: Statistical Barriers and Opportunities
536. ICLR 2026Learning Distributions over Permutations and Rankings with Factorized Representations
537. ICLR 2026Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
538. ICLR 2026Learning Ordinal Probabilistic Reward from Preferences
539. ICLR 2026Learning to summarize user information for personalized reinforcement learning from human feedback
540. ICLR 2026Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment
541. ICLR 2026Learning-Time Encoding Shapes Unlearning in LLMs
542. ICLR 2026Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
543. ICLR 2026LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
544. ICLR 2026LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization
545. ICLR 2026LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion
546. ICLR 2026LLM Fingerprinting via Semantically Conditioned Watermarks
547. ICLR 2026LLM Unlearning with LLM Beliefs
548. ICLR 2026LLMs Can Hide Text in Other Text of the Same Length
549. ICLR 2026LLMS ON TRIAL: Evaluating Judicial Fairness For Large Language Models
550. ICLR 2026Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis

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.