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

1,421 papers, page 14 of 29

651. NeurIPS 2025Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
652. NeurIPS 2025Graph Alignment via Birkhoff Relaxation
653. NeurIPS 2025GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
654. NeurIPS 2025Greedy Sampling Is Provably Efficient For RLHF
655. NeurIPS 2025GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
656. NeurIPS 2025GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
657. NeurIPS 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling
658. NeurIPS 2025Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment
659. NeurIPS 2025Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
660. NeurIPS 2025Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
661. NeurIPS 2025HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
662. NeurIPS 2025Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
663. NeurIPS 2025Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
664. NeurIPS 2025How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
665. NeurIPS 2025Human-assisted Robotic Policy Refinement via Action Preference Optimization
666. NeurIPS 2025HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
667. NeurIPS 2025HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning
668. NeurIPS 2025Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies
669. NeurIPS 2025Impact of Layer Norm on Memorization and Generalization in Transformers
670. NeurIPS 2025Impartial Selection with Predictions
671. NeurIPS 2025Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
672. NeurIPS 2025Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
673. NeurIPS 2025Improved Bounds for Swap Multicalibration and Swap Omniprediction
674. NeurIPS 2025Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits
675. NeurIPS 2025Improved Representation Steering for Language Models
676. NeurIPS 2025Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
677. NeurIPS 2025Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
678. NeurIPS 2025Improving Video Generation with Human Feedback
679. NeurIPS 2025Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion
680. NeurIPS 2025Incomplete Multi-view Deep Clustering with Data Imputation and Alignment
681. NeurIPS 2025Inference-time Alignment in Continuous Space
682. NeurIPS 2025Inference-Time Personalized Alignment with a Few User Preference Queries
683. NeurIPS 2025Inference-Time Reward Hacking in Large Language Models
684. NeurIPS 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
685. NeurIPS 2025Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
686. NeurIPS 2025InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
687. NeurIPS 2025Information Retrieval Induced Safety Degradation in AI Agents
688. NeurIPS 2025Information-Theoretic Reward Decomposition for Generalizable RLHF
689. NeurIPS 2025Infrequent Exploration in Linear Bandits
690. NeurIPS 2025Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation
691. NeurIPS 2025Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval
692. NeurIPS 2025InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
693. NeurIPS 2025IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
694. NeurIPS 2025JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics
695. NeurIPS 2025JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
696. NeurIPS 2025Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
697. NeurIPS 2025KL Penalty Control via Perturbation for Direct Preference Optimization
698. NeurIPS 2025KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
699. NeurIPS 2025LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process
700. NeurIPS 2025Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale

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.