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

875 papers, page 8 of 18

351. ICML 2024Estimating Canopy Height at Scale
352. ICML 2024Expand-and-Cluster: Parameter Recovery of Neural Networks
353. ICML 2024Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
354. ICML 2024Exploring the LLM Journey from Cognition to Expression with Linear Representations
355. ICML 2024Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
356. ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
357. ICML 2024FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
358. ICML 2024FESSNC: Fast Exponentially Stable and Safe Neural Controller
359. ICML 2024Flextron: Many-in-One Flexible Large Language Model
360. ICML 2024From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
361. ICML 2024Fundamental Limitations of Alignment in Large Language Models
362. ICML 2024Generalized Preference Optimization: A Unified Approach to Offline Alignment
363. ICML 2024GNNs Also Deserve Editing, and They Need It More Than Once
364. ICML 2024Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
365. ICML 2024GRATH: Gradual Self-Truthifying for Large Language Models
366. ICML 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
367. ICML 2024Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
368. ICML 2024High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference Cost
369. ICML 2024How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
370. ICML 2024How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
371. ICML 2024How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
372. ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
373. ICML 2024IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
374. ICML 2024Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
375. ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
376. ICML 2024Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
377. ICML 2024Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
378. ICML 2024In-Context Language Learning: Architectures and Algorithms
379. ICML 2024In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
380. ICML 2024InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
381. ICML 2024Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification
382. ICML 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
383. ICML 2024Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
384. ICML 2024Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
385. ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
386. ICML 2024Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs
387. ICML 2024KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations
388. ICML 2024Language Models Represent Beliefs of Self and Others
389. ICML 2024LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
390. ICML 2024Learning and Forgetting Unsafe Examples in Large Language Models
391. ICML 2024Learning Associative Memories with Gradient Descent
392. ICML 2024Learning Decision Trees and Forests with Algorithmic Recourse
393. ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
394. ICML 2024Learning Linear Block Error Correction Codes
395. ICML 2024Learning Modality Knowledge Alignment for Cross-Modality Transfer
396. ICML 2024Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
397. ICML 2024Learning to Remove Cuts in Integer Linear Programming
398. ICML 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)
399. ICML 2024Limited Preference Aided Imitation Learning from Imperfect Demonstrations
400. ICML 2024Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

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.