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 13 of 28

601. ICLR 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
602. ICLR 2025Wasserstein Distances, Neuronal Entanglement, and Sparsity
603. ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
604. ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
605. ICLR 2025Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
606. ICLR 2025X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
607. ICLR 2025Your Weak LLM is Secretly a Strong Teacher for Alignment
608. ICLR 2025Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
609. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
610. ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
611. ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
612. ICML 2025A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity
613. ICML 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
614. ICML 2025A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
615. ICML 2025A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
616. ICML 2025Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
617. ICML 2025Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
618. ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models
619. ICML 2025Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment
620. ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
621. ICML 2025Adaptive Estimation and Learning under Temporal Distribution Shift
622. ICML 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
623. ICML 2025ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
624. ICML 2025AdvAgent: Controllable Blackbox Red-teaming on Web Agents
625. ICML 2025Adversaries Can Misuse Combinations of Safe Models
626. ICML 2025AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
627. ICML 2025AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation
628. ICML 2025Aligning Multimodal Representations through an Information Bottleneck
629. ICML 2025Aligning Spoken Dialogue Models from User Interactions
630. ICML 2025Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
631. ICML 2025AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
632. ICML 2025AlphaPO: Reward Shape Matters for LLM Alignment
633. ICML 2025AMPO: Active Multi Preference Optimization for Self-play Preference Selection
634. ICML 2025Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
635. ICML 2025Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
636. ICML 2025Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
637. ICML 2025Avoiding Catastrophe in Online Learning by Asking for Help
638. ICML 2025Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
639. ICML 2025BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition
640. ICML 2025Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
641. ICML 2025Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
642. ICML 2025BILBO: BILevel Bayesian Optimization
643. ICML 2025Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training
644. ICML 2025BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
645. ICML 2025Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
646. ICML 2025BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization
647. ICML 2025Breaking Barriers: Combinatorial Algorithms for Non-Monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation
648. ICML 2025Calibrated Language Models and How to Find Them with Label Smoothing
649. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
650. ICML 2025Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

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.