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 87 of 92

4301. ICLR 2023Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow
4302. ICLR 2023SYNC: SAFETY-AWARE NEURAL CONTROL FOR STABILIZING STOCHASTIC DELAY-DIFFERENTIAL EQUATIONS
4303. ICLR 2023TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
4304. ICLR 2023Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
4305. ICLR 2023Task Ambiguity in Humans and Language Models
4306. ICLR 2023TempCLR: Temporal Alignment Representation with Contrastive Learning
4307. ICLR 2023Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations
4308. ICLR 2023Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case
4309. ICLR 2023Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
4310. ICLR 2023Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
4311. ICLR 2023Training language models to summarize narratives improves brain alignment
4312. ICLR 2023Understanding Influence Functions and Datamodels via Harmonic Analysis
4313. ICLR 2023Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
4314. ICLR 2023Unsupervised Manifold Alignment with Joint Multidimensional Scaling
4315. ICLR 2023Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
4316. ICLR 2023What Is Missing in IRM Training and Evaluation? Challenges and Solutions
4317. ICLR 2023When to Make and Break Commitments?
4318. ICLR 2023Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
4319. ICLR 2023Why (and When) does Local SGD Generalize Better than SGD?
4320. ICML 2023A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates
4321. ICML 2023A Modern Look at the Relationship between Sharpness and Generalization
4322. ICML 2023A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
4323. ICML 2023A Study on Transformer Configuration and Training Objective
4324. ICML 2023A Theoretical Analysis of the Learning Dynamics under Class Imbalance
4325. ICML 2023abess: A Fast Best-Subset Selection Library in Python and R
4326. ICML 2023Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations
4327. ICML 2023Adversarial Classification: Necessary Conditions and Geometric Flows
4328. ICML 2023Aligning Language Models with Preferences through $f$-divergence Minimization
4329. ICML 2023Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation
4330. ICML 2023Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
4331. ICML 2023Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
4332. ICML 2023Bandit Online Linear Optimization with Hints and Queries
4333. ICML 2023Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
4334. ICML 2023Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies
4335. ICML 2023Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
4336. ICML 2023Constrained Phi-Equilibria
4337. ICML 2023Contextual Conservative Interleaving Bandits
4338. ICML 2023Contextual Reliability: When Different Features Matter in Different Contexts
4339. ICML 2023Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction
4340. ICML 2023Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss
4341. ICML 2023Cut your Losses with Squentropy
4342. ICML 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark
4343. ICML 2023DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
4344. ICML 2023DUET: 2D Structured and Approximately Equivariant Representations
4345. ICML 2023EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression
4346. ICML 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
4347. ICML 2023Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration
4348. ICML 2023Expected Gradients of Maxout Networks and Consequences to Parameter Initialization
4349. ICML 2023Explainable Data-Driven Optimization: From Context to Decision and Back Again
4350. ICML 2023FAIRER: Fairness as Decision Rationale Alignment

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.