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

1,421 papers, page 1 of 29

1. NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
2. NeurIPS 2026$\mathcal{P}$Torch: Narrowing the Gap Between Projection and Gradient-Based Learning
3. NeurIPS 2026A Compass for Useful Data: Online Data Selection via Alignment-Gated Fisher Geometry
4. NeurIPS 2026A Computational Perspective to Data Ablation Experiments
5. NeurIPS 2026A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds
6. NeurIPS 2026A Provably Convergent and Practical Algorithm for Gromov–Wasserstein Optimal Transport
7. NeurIPS 2026A simple model of co-emergence of grid and place fields
8. NeurIPS 2026A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
9. NeurIPS 2026A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
10. NeurIPS 2026A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics
11. NeurIPS 2026A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning
12. NeurIPS 2026A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
13. NeurIPS 2026ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
14. NeurIPS 2026AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation
15. NeurIPS 2026Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
16. NeurIPS 2026Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
17. NeurIPS 2026Adapting to Conflict: Equilibrium Structure and Adaptive Learning in Harmonic Games
18. NeurIPS 2026Adaptive Covariance and Multi-Layer Alignment for Out-of-Distribution Detection
19. NeurIPS 2026Adaptive Random Forests from Online Learning and Testing by Betting
20. NeurIPS 2026AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising
21. NeurIPS 2026Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models
22. NeurIPS 2026AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
23. NeurIPS 2026AesGI-Bench: Benchmarking and Evaluating the Aesthetic Quality of AI-Generated Images via Large Multimodal Models
24. NeurIPS 2026Affine-invariant Cubic Newton with Weak Learners
25. NeurIPS 2026Agentic Multi-Turn Reasoning: A Fairness Approach
26. NeurIPS 2026AI Control for Sandbagging on Fuzzy Tasks
27. NeurIPS 2026AI-Assisted Classification under Correlation Neglect and Trust
28. NeurIPS 2026Algorithmic Impact Reveals the Hidden Structure of Alignment
29. NeurIPS 2026Align $\&$ Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
30. NeurIPS 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
31. NeurIPS 2026Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHF
32. NeurIPS 2026Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
33. NeurIPS 2026Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
34. NeurIPS 2026Alignment Is Not Enough for Safe Medical LLM Evaluation
35. NeurIPS 2026AlphaPROBE: Alpha Mining via principled retriveval and on-graph biased evolution
36. NeurIPS 2026AMARIS: Merging Generalist and Specialist LLMs via Adaptive Subspace Inheritance
37. NeurIPS 2026AMPS: Adaptive Modality Preference Steering via Functional Entropy
38. NeurIPS 2026An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
39. NeurIPS 2026An Axiomatic Analysis of DPO and NLHF as Reference-Dependent Probabilistic Voting Rules
40. NeurIPS 2026An Educated Guess: Deriving Statistically Aligned Gradient Estimates for Zeroth-Order Optimization
41. NeurIPS 2026An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
42. NeurIPS 2026An Equivariance Principle for Optimizer Design: Symmetry-Compatible Updates for Embeddings, LM Heads, and MoE Routers
43. NeurIPS 2026Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test
44. NeurIPS 2026As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does
45. NeurIPS 2026AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism
46. NeurIPS 2026Attack Selection In Agentic AI Control Evaluations Meaningfully Decreases Safety
47. NeurIPS 2026Attention Alignment Between Humans and Vision-Language Models
48. NeurIPS 2026Attention Sinks and Outliers in Attention Residuals
49. NeurIPS 2026Attention-Based Soft Answer Sets
50. NeurIPS 2026Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases

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.