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

455 papers, page 1 of 10

1. NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
2. NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
3. NeurIPS 2025$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
4. NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
5. NeurIPS 2025A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
6. NeurIPS 2025A faster training algorithm for regression trees with linear leaves, and an analysis of its complexity
7. NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
8. NeurIPS 2025A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
9. NeurIPS 2025A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
10. NeurIPS 2025AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
11. NeurIPS 2025Accident Anticipation via Temporal Occurrence Prediction
12. NeurIPS 2025Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning
13. NeurIPS 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
14. NeurIPS 2025Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
15. NeurIPS 2025Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
16. NeurIPS 2025Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
17. NeurIPS 2025AdvPrefix: An Objective for Nuanced LLM Jailbreaks
18. NeurIPS 2025AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering
19. NeurIPS 2025Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
20. NeurIPS 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
21. NeurIPS 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
22. NeurIPS 2025AI-Generated Video Detection via Perceptual Straightening
23. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
24. NeurIPS 2025Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
25. NeurIPS 2025Aligning Compound AI Systems via System-level DPO
26. NeurIPS 2025Aligning Text to Image in Diffusion Models is Easier Than You Think
27. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
28. NeurIPS 2025Alignment of Large Language Models with Constrained Learning
29. NeurIPS 2025AliO: Output Alignment Matters in Long-Term Time Series Forecasting
30. NeurIPS 2025ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
31. NeurIPS 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
32. NeurIPS 2025An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
33. NeurIPS 2025Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
34. NeurIPS 2025Angular Steering: Behavior Control via Rotation in Activation Space
35. NeurIPS 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
36. NeurIPS 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain
37. NeurIPS 2025Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
38. NeurIPS 2025Attention Mechanism, Max-Affine Partition, and Universal Approximation
39. NeurIPS 2025Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
40. NeurIPS 2025Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
41. NeurIPS 2025AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving
42. NeurIPS 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
43. NeurIPS 2025Avoiding exp(R) scaling in RLHF through Preference-based Exploration
44. NeurIPS 2025Backdoor Cleaning without External Guidance in MLLM Fine-tuning
45. NeurIPS 2025BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
46. NeurIPS 2025Bag of Tricks for Inference-time Computation of LLM Reasoning
47. NeurIPS 2025Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning
48. NeurIPS 2025Bandit and Delayed Feedback in Online Structured Prediction
49. NeurIPS 2025Best-of-N Jailbreaking
50. NeurIPS 2025Better Estimation of the Kullback--Leibler Divergence Between Language Models

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.