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 15 of 28

701. ICML 2025FlipAttack: Jailbreak LLMs via Flipping
702. ICML 2025Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics
703. ICML 2025Functional Alignment Can Mislead: Examining Model Stitching
704. ICML 2025Fusing Reward and Dueling Feedback in Stochastic Bandits
705. ICML 2025Gandalf the Red: Adaptive Security for LLMs
706. ICML 2025Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
707. ICML 2025Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization
708. ICML 2025Global Optimization with a Power-Transformed Objective and Gaussian Smoothing
709. ICML 2025Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes
710. ICML 2025GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code
711. ICML 2025GRAM: A Generative Foundation Reward Model for Reward Generalization
712. ICML 2025Hardware and Software Platform Inference
713. ICML 2025Hierarchical Graph Tokenization for Molecule-Language Alignment
714. ICML 2025How to set AdamW's weight decay as you scale model and dataset size
715. ICML 2025HPS: Hard Preference Sampling for Human Preference Alignment
716. ICML 2025Human-Aligned Image Models Improve Visual Decoding from the Brain
717. ICML 2025ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
718. ICML 2025Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
719. ICML 2025Improving LLM Safety Alignment with Dual-Objective Optimization
720. ICML 2025Improving Model Alignment Through Collective Intelligence of Open-Source Models
721. ICML 2025Improving Multimodal Learning Balance and Sufficiency through Data Remixing
722. ICML 2025InfAlign: Inference-aware language model alignment
723. ICML 2025Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
724. ICML 2025Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
725. ICML 2025Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
726. ICML 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
727. ICML 2025Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
728. ICML 2025Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization
729. ICML 2025Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
730. ICML 2025Kernel Quantile Embeddings and Associated Probability Metrics
731. ICML 2025Knowledge Swapping via Learning and Unlearning
732. ICML 2025Knowledge-Guided Wasserstein Distributionally Robust Optimization
733. ICML 2025Language Models as Implicit Tree Search
734. ICML 2025LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
735. ICML 2025Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
736. ICML 2025Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
737. ICML 2025Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
738. ICML 2025Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
739. ICML 2025Learning Cascade Ranking as One Network
740. ICML 2025Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
741. ICML 2025Learning Safety Constraints for Large Language Models
742. ICML 2025Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
743. ICML 2025Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
744. ICML 2025Learnware Specification via Dual Alignment
745. ICML 2025Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective
746. ICML 2025Linear Bandits with Partially Observable Features
747. ICML 2025LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
748. ICML 2025LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
749. ICML 2025LLM Data Selection and Utilization via Dynamic Bi-level Optimization
750. ICML 2025Logarithmic Regret for Online KL-Regularized Reinforcement Learning

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.