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

4,558 papers, page 72 of 92

3551. ICML 2024BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
3552. ICML 2024Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
3553. ICML 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
3554. ICML 2024Can AI Assistants Know What They Don't Know?
3555. ICML 2024Can Machines Learn the True Probabilities?
3556. ICML 2024CARTE: Pretraining and Transfer for Tabular Learning
3557. ICML 2024Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
3558. ICML 2024Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
3559. ICML 2024Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
3560. ICML 2024Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free Inference
3561. ICML 2024CogBench: a large language model walks into a psychology lab
3562. ICML 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
3563. ICML 2024Compressing Large Language Models by Joint Sparsification and Quantization
3564. ICML 2024Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration
3565. ICML 2024Contrastive Predict-and-Search for Mixed Integer Linear Programs
3566. ICML 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
3567. ICML 2024Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
3568. ICML 2024Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
3569. ICML 2024Convex and Bilevel Optimization for Neural-Symbolic Inference and Learning
3570. ICML 2024Criterion Collapse and Loss Distribution Control
3571. ICML 2024DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
3572. ICML 2024Decoding-time Realignment of Language Models
3573. ICML 2024Decomposable Submodular Maximization in Federated Setting
3574. ICML 2024Deconstructing the Goldilocks Zone of Neural Network Initialization
3575. ICML 2024Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods
3576. ICML 2024Deep Networks Always Grok and Here is Why
3577. ICML 2024Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
3578. ICML 2024Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
3579. ICML 2024Dense Reward for Free in Reinforcement Learning from Human Feedback
3580. ICML 2024Detecting and Identifying Selection Structure in Sequential Data
3581. ICML 2024Differentiability and Optimization of Multiparameter Persistent Homology
3582. ICML 2024Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
3583. ICML 2024Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery
3584. ICML 2024Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification
3585. ICML 2024Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset
3586. ICML 2024Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
3587. ICML 2024EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism
3588. ICML 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
3589. ICML 2024Emergent Equivariance in Deep Ensembles
3590. ICML 2024Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
3591. ICML 2024Enhancing Implicit Shape Generators Using Topological Regularizations
3592. ICML 2024Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models
3593. ICML 2024Equivariant Deep Weight Space Alignment
3594. ICML 2024Equivariant Frames and the Impossibility of Continuous Canonicalization
3595. ICML 2024Estimating Barycenters of Distributions with Neural Optimal Transport
3596. ICML 2024Estimating Canopy Height at Scale
3597. ICML 2024Expand-and-Cluster: Parameter Recovery of Neural Networks
3598. ICML 2024Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
3599. ICML 2024Exploring the LLM Journey from Cognition to Expression with Linear Representations
3600. ICML 2024Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training

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.