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

246 papers, page 1 of 5

1. ICML 2024A connection between Tempering and Entropic Mirror Descent
2. ICML 2024A Global Geometric Analysis of Maximal Coding Rate Reduction
3. ICML 2024A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
4. ICML 2024A Minimaximalist Approach to Reinforcement Learning from Human Feedback
5. ICML 2024A Neural-Preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
6. ICML 2024A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
7. ICML 2024Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
8. ICML 2024Active Preference Learning for Large Language Models
9. ICML 2024Active Ranking and Matchmaking, with Perfect Matchings
10. ICML 2024Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
11. ICML 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
12. ICML 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
13. ICML 2024Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms
14. ICML 2024AI Alignment with Changing and Influenceable Reward Functions
15. ICML 2024AI Control: Improving Safety Despite Intentional Subversion
16. ICML 2024Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models
17. ICML 2024Aligning Transformers with Weisfeiler-Leman
18. ICML 2024AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
19. ICML 2024An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization
20. ICML 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
21. ICML 2024AutoOS: Make Your OS More Powerful by Exploiting Large Language Models
22. ICML 2024Balanced Resonate-and-Fire Neurons
23. ICML 2024Balancing Similarity and Complementarity for Federated Learning
24. ICML 2024Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium
25. ICML 2024BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
26. ICML 2024Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
27. ICML 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
28. ICML 2024Can AI Assistants Know What They Don't Know?
29. ICML 2024Can Machines Learn the True Probabilities?
30. ICML 2024CARTE: Pretraining and Transfer for Tabular Learning
31. ICML 2024Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
32. ICML 2024Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
33. ICML 2024Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
34. ICML 2024Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free Inference
35. ICML 2024CogBench: a large language model walks into a psychology lab
36. ICML 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
37. ICML 2024Compressing Large Language Models by Joint Sparsification and Quantization
38. ICML 2024Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration
39. ICML 2024Contrastive Predict-and-Search for Mixed Integer Linear Programs
40. ICML 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
41. ICML 2024Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
42. ICML 2024Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
43. ICML 2024Convex and Bilevel Optimization for Neural-Symbolic Inference and Learning
44. ICML 2024Criterion Collapse and Loss Distribution Control
45. ICML 2024DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
46. ICML 2024Decoding-time Realignment of Language Models
47. ICML 2024Decomposable Submodular Maximization in Federated Setting
48. ICML 2024Deconstructing the Goldilocks Zone of Neural Network Initialization
49. ICML 2024Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods
50. ICML 2024Deep Networks Always Grok and Here is Why

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.