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

1,198 papers, page 1 of 24

1. ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
2. ICML 2026$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
3. ICML 2026A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
4. ICML 2026A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
5. ICML 2026A Game-Theoretic Analysis of Attacks on Large Language Models via Compositional Skills
6. ICML 2026A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs
7. ICML 2026A New Framework for Cybersecurity Refusals in AI Agents
8. ICML 2026A Perturbation Approach to Unconstrained Linear Bandits
9. ICML 2026A Positive Case for Faithfulness: Explanations Help Predict Model Behavior
10. ICML 2026A Regret Minimization Framework on Preference Learning in Large Language Models
11. ICML 2026A Robust Optimization Guided Pruning Framework for Vision and Large Language Models
12. ICML 2026A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
13. ICML 2026A Two-Layer Framework for Joint Online Configuration Selection and Admission Control
14. ICML 2026A-MemGuard: A Proactive Defense Framework For LLM-Based Agent Memory
15. ICML 2026Abstraction Induces the Brain Alignment of Language and Speech Models
16. ICML 2026Achieving Structurally Robust Gromov Wasserstein Distance via Adaptive Dual-Mask
17. ICML 2026Active Attacks: Red-teaming LLMs via Adaptive Environments
18. ICML 2026ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
19. ICML 2026Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
20. ICML 2026AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally
21. ICML 2026Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
22. ICML 2026AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
23. ICML 2026AICrypto: Evaluating Cryptography Capabilities of Large Language Models
24. ICML 2026AIR: Improving Agent Safety through Incident Response
25. ICML 2026Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
26. ICML 2026Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
27. ICML 2026Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
28. ICML 2026Alignment Risks from Capability-Seeking RL Training
29. ICML 2026Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
30. ICML 2026Alignment-Aware Decoding
31. ICML 2026An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
32. ICML 2026Anatomy of Massive Activations and Attention Sinks
33. ICML 2026ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
34. ICML 2026Anytime Safe PAC Efficient Reasoning
35. ICML 2026Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
36. ICML 2026Are Your Agents Upward Deceivers?
37. ICML 2026Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling
38. ICML 2026Attention Sinks in Diffusion Transformers: A Causal Analysis
39. ICML 2026Attention's forward pass and Frank-Wolfe
40. ICML 2026Attributed Network Alignment: Statistical Limits and Efficient Algorithm
41. ICML 2026Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
42. ICML 2026AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
43. ICML 2026Automatically Finding Reward Model Biases
44. ICML 2026Autoregressive Direct Preference Optimization
45. ICML 2026AvAtar: Learning to Align via Active Optimal Transport
46. ICML 2026Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
47. ICML 2026Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series Distillation
48. ICML 2026Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
49. ICML 2026BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
50. ICML 2026Blending Neural Control Density Functions for Stabilization and Safety

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.