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

1,339 papers, page 1 of 27

1. ICLR 2026(Token-Level) \textbf{InfoRMIA}: Stronger Membership Inference and Privacy Assessment for LLMs
2. ICLR 2026$\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ Divergence
3. ICLR 2026A Fair Bayesian Inference through Matched Gibbs Posterior
4. ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
5. ICLR 2026A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
6. ICLR 2026A Unified Total Variation Framework for Membrane Potential Perturbation Dynamic
7. ICLR 2026A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
8. ICLR 2026Activation Steering for LLM Alignment via a Unified ODE-Based Framework
9. ICLR 2026Activation Steering with a Feedback Controller
10. ICLR 2026ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
11. ICLR 2026AdAEM: An Adaptively and Automated Extensible Evaluation Method of LLMs' Value Difference
12. ICLR 2026Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
13. ICLR 2026Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
14. ICLR 2026Adaptive Social Learning via Mode Policy Optimization for Language Agents
15. ICLR 2026AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization
16. ICLR 2026AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
17. ICLR 2026Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
18. ICLR 2026Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
19. ICLR 2026Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
20. ICLR 2026Align-SAM: Seeking Flatter Minima for Better Cross-Subset Alignment
21. ICLR 2026Aligner, Diagnose Thyself: A Meta-Learning Paradigm for Fusing Intrinsic Feedback in Preference Alignment
22. ICLR 2026Aligning Collaborative View Recovery and Tensorial Subspace Learning via Latent Representation for Incomplete Multi-View Clustering
23. ICLR 2026Aligning Deep Implicit Preferences by Learning to Reason Defensively
24. ICLR 2026Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
25. ICLR 2026Alignment-Enhanced Integration of Connectivity and Spectral Sparse in Dynamic Sparse Training of LLM
26. ICLR 2026Alignment-Weighted DPO: A principled reasoning approach to improve alignment
27. ICLR 2026AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching
28. ICLR 2026All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
29. ICLR 2026All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning
30. ICLR 2026AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
31. ICLR 2026AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
32. ICLR 2026Annotation-Efficient Honesty Alignment via Confidence Elicitation and Calibration
33. ICLR 2026Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
34. ICLR 2026Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
35. ICLR 2026Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
36. ICLR 2026Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
37. ICLR 2026Are Deep Speech Denoising Models Robust to Adversarial Noise?
38. ICLR 2026ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
39. ICLR 2026ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
40. ICLR 2026ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
41. ICLR 2026ASIDE: Architectural Separation of Instructions and Data in Language Models
42. ICLR 2026Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
43. ICLR 2026Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation
44. ICLR 2026Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
45. ICLR 2026Attention Smoothing Is All You Need For Unlearning
46. ICLR 2026AttriCtrl: A Generalizable Framework for Controlling Semantic Attribute Intensity in Diffusion Models
47. ICLR 2026AttTok: Marrying Attribute Tokens with Generative Pre-trained Vision-Language Models towards Medical Image Understanding
48. ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
49. ICLR 2026Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
50. ICLR 2026Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies

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.