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 15 of 38

701. ICLR 2026SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input Routing
702. ICLR 2026Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
703. ICLR 2026Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
704. ICLR 2026Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
705. ICLR 2026Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
706. ICLR 2026SAGA: Structural Aggregation Guided Alignment with Dynamic View and Neighborhood Order Selection for Multiview Graph Domain Adaptation
707. ICLR 2026Sample Reward Soups: Query-efficient Multi-Reward Guidance for Text-to-Image Diffusion Models
708. ICLR 2026Sampling-aware Adversarial Attacks Against Large Language Models
709. ICLR 2026SDErasure: Concept-Specific Trajectory Shifting for Concept Erasure via Adaptive Diffusion Classifier
710. ICLR 2026SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC
711. ICLR 2026Secret-Protected Evolution for Differentially Private Synthetic Text Generation
712. ICLR 2026Secure Outlier-Aware Large Language Model Inference
713. ICLR 2026SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing
714. ICLR 2026SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
715. ICLR 2026Seeing What’s Wrong: A Trajectory-Guided Approach to Caption Error Detection
716. ICLR 2026Selective Data Removal for Distributional Machine Unlearning
717. ICLR 2026Self-Destructive Language Models
718. ICLR 2026Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
719. ICLR 2026SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
720. ICLR 2026Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
721. ICLR 2026Semi-Supervised Preference Optimization with Limited Feedback
722. ICLR 2026SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box Attacks
723. ICLR 2026Set Representation Auxiliary Learning with Adversarial Encoding Perturbation and Optimization
724. ICLR 2026Sharpness-Aware Machine Unlearning
725. ICLR 2026Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
726. ICLR 2026SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video Diffusion
727. ICLR 2026Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems
728. ICLR 2026SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
729. ICLR 2026Skirting Additive Error Lower Bounds for Private Turnstile Streams
730. ICLR 2026sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals
731. ICLR 2026SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks
732. ICLR 2026SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
733. ICLR 2026SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
734. ICLR 2026SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
735. ICLR 2026Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
736. ICLR 2026SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge
737. ICLR 2026SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
738. ICLR 2026Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
739. ICLR 2026SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
740. ICLR 2026SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
741. ICLR 2026Spilled Energy in Large Language Models
742. ICLR 2026Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
743. ICLR 2026ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
744. ICLR 2026Stable and Scalable Deep Predictive Coding Networks with Meta Prediction Errors
745. ICLR 2026Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game
746. ICLR 2026STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language Model
747. ICLR 2026Statistical Guarantees in the Search for Less Discriminatory Algorithms
748. ICLR 2026Steerable Adversarial Scenario Generation through Test-Time Preference Alignment
749. ICLR 2026Steering Evaluation-Aware Language Models To Act Like They Are Deployed
750. ICLR 2026Steering Language Models with Weight Arithmetic

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.