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

473 papers, page 1 of 10

1. ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
2. ICLR 2025$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning
3. ICLR 20253D-Properties: Identifying Challenges in DPO and Charting a Path Forward
4. ICLR 2025A Benchmark for Semantic Sensitive Information in LLMs Outputs
5. ICLR 2025A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
6. ICLR 2025A Closer Look at Machine Unlearning for Large Language Models
7. ICLR 2025A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
8. ICLR 2025A Generic Framework for Conformal Fairness
9. ICLR 2025A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
10. ICLR 2025A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
11. ICLR 2025A Simple yet Effective $\Delta\Delta G$ Predictor is An Unsupervised Antibody Optimizer and Explainer
12. ICLR 2025A Theoretical Framework for Partially-Observed Reward States in RLHF
13. ICLR 2025A Transfer Attack to Image Watermarks
14. ICLR 2025A transfer learning framework for weak to strong generalization
15. ICLR 2025ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
16. ICLR 2025Accelerating Training with Neuron Interaction and Nowcasting Networks
17. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
18. ICLR 2025Adam-mini: Use Fewer Learning Rates To Gain More
19. ICLR 2025Adaptive Batch Size for Privately Finding Second-Order Stationary Points
20. ICLR 2025Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
21. ICLR 2025Adaptive Energy Alignment for Accelerating Test-Time Adaptation
22. ICLR 2025Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
23. ICLR 2025Advancing LLM Reasoning Generalists with Preference Trees
24. ICLR 2025Advantage-Guided Distillation for Preference Alignment in Small Language Models
25. ICLR 2025Adversarial Attacks on Data Attribution
26. ICLR 2025Adversarial Latent Feature Augmentation for Fairness
27. ICLR 2025Adversarial Machine Unlearning
28. ICLR 2025Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
29. ICLR 2025Adversarial Search Engine Optimization for Large Language Models
30. ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
31. ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
32. ICLR 2025AI Sandbagging: Language Models can Strategically Underperform on Evaluations
33. ICLR 2025AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories
34. ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
35. ICLR 2025Aligned LLMs Are Not Aligned Browser Agents
36. ICLR 2025Aligning Language Models with Demonstrated Feedback
37. ICLR 2025Aligning Visual Contrastive learning models via Preference Optimization
38. ICLR 2025ALLaM: Large Language Models for Arabic and English
39. ICLR 2025AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
40. ICLR 2025Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
41. ICLR 2025An Auditing Test to Detect Behavioral Shift in Language Models
42. ICLR 2025An Effective Theory of Bias Amplification
43. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
44. ICLR 2025An Undetectable Watermark for Generative Image Models
45. ICLR 2025Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
46. ICLR 2025As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
47. ICLR 2025Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
48. ICLR 2025Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation
49. ICLR 2025Attention with Markov: A Curious Case of Single-layer Transformers
50. ICLR 2025AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

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.