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 16 of 29

751. NeurIPS 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
752. NeurIPS 2025On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
753. NeurIPS 2025On Evaluating LLM Alignment by Evaluating LLMs as Judges
754. NeurIPS 2025On Extending Direct Preference Optimization to Accommodate Ties
755. NeurIPS 2025On Local Limits of Sparse Random Graphs: Color Convergence and the Refined Configuration Model
756. NeurIPS 2025On the creation of narrow AI: hierarchy and nonlocality of neural network skills
757. NeurIPS 2025On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
758. NeurIPS 2025On the Existence and Complexity of Core-Stable Data Exchanges
759. NeurIPS 2025On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels
760. NeurIPS 2025On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
761. NeurIPS 2025One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
762. NeurIPS 2025Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
763. NeurIPS 2025Online Strategic Classification With Noise and Partial Feedback
764. NeurIPS 2025OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
765. NeurIPS 2025Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
766. NeurIPS 2025OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
767. NeurIPS 2025Orthogonal Contrastive Learning for Multi-Representation fMRI Analysis
768. NeurIPS 2025OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
769. NeurIPS 2025Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
770. NeurIPS 2025OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
771. NeurIPS 2025Pairwise Calibrated Rewards for Pluralistic Alignment
772. NeurIPS 2025Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
773. NeurIPS 2025Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies
774. NeurIPS 2025PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network
775. NeurIPS 2025Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization
776. NeurIPS 2025Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach
777. NeurIPS 2025Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning
778. NeurIPS 2025PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
779. NeurIPS 2025PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors
780. NeurIPS 2025Position: Bridge the Gaps between Machine Unlearning and AI Regulation
781. NeurIPS 2025Position: Require Frontier AI Labs To Release Small "Analog" Models
782. NeurIPS 2025Position: Towards Bidirectional Human-AI Alignment
783. NeurIPS 2025Pre-Trained Policy Discriminators are General Reward Models
784. NeurIPS 2025Predictive Preference Learning from Human Interventions
785. NeurIPS 2025Preference Distillation via Value based Reinforcement Learning
786. NeurIPS 2025Preference Learning with Lie Detectors can Induce Honesty or Evasion
787. NeurIPS 2025Preference Learning with Response Time: Robust Losses and Guarantees
788. NeurIPS 2025Preference Optimization by Estimating the Ratio of the Data Distribution
789. NeurIPS 2025Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
790. NeurIPS 2025Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
791. NeurIPS 2025Prior Forgetting and In-Context Overfitting
792. NeurIPS 2025Probabilistic Stability Guarantees for Feature Attributions
793. NeurIPS 2025Probabilistic Token Alignment for Large Language Model Fusion
794. NeurIPS 2025Prohibiting Generative AI in any Form of Weapon Control
795. NeurIPS 2025Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a Restorer
796. NeurIPS 2025Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
797. NeurIPS 2025Protein Inverse Folding From Structure Feedback
798. NeurIPS 2025Provably Efficient Online RLHF with One-Pass Reward Modeling
799. NeurIPS 2025Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO
800. NeurIPS 2025PurpCode: Reasoning for Safer Code Generation

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.