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

156 papers, page 1 of 4

1. ICLR 2024#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
2. ICLR 2024A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
3. ICLR 2024A unique M-pattern for micro-expression spotting in long videos
4. ICLR 2024Adversarial Training Should Be Cast as a Non-Zero-Sum Game
5. ICLR 2024Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
6. ICLR 2024Aligning Relational Learning with Lipschitz Fairness
7. ICLR 2024An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment
8. ICLR 2024An Emulator for Fine-tuning Large Language Models using Small Language Models
9. ICLR 2024An Investigation of Representation and Allocation Harms in Contrastive Learning
10. ICLR 2024An Unforgeable Publicly Verifiable Watermark for Large Language Models
11. ICLR 2024ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
12. ICLR 2024ARGS: Alignment as Reward-Guided Search
13. ICLR 2024AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
14. ICLR 2024Backdoor Contrastive Learning via Bi-level Trigger Optimization
15. ICLR 2024BadEdit: Backdooring Large Language Models by Model Editing
16. ICLR 2024Benchmarking and Improving Generator-Validator Consistency of Language Models
17. ICLR 2024Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
18. ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
19. ICLR 2024Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
20. ICLR 2024Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
21. ICLR 2024Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
22. ICLR 2024Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
23. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
24. ICLR 2024Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
25. ICLR 2024CAS: A Probability-Based Approach for Universal Condition Alignment Score
26. ICLR 2024Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
27. ICLR 2024Chain of Hindsight aligns Language Models with Feedback
28. ICLR 2024Classification with Conceptual Safeguards
29. ICLR 2024Compositional Preference Models for Aligning LMs
30. ICLR 2024Compressing LLMs: The Truth is Rarely Pure and Never Simple
31. ICLR 2024Confidential-DPproof: Confidential Proof of Differentially Private Training
32. ICLR 2024Confronting Reward Model Overoptimization with Constrained RLHF
33. ICLR 2024Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
34. ICLR 2024Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
35. ICLR 2024Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
36. ICLR 2024CPPO: Continual Learning for Reinforcement Learning with Human Feedback
37. ICLR 2024Curiosity-driven Red-teaming for Large Language Models
38. ICLR 2024Debiasing Attention Mechanism in Transformer without Demographics
39. ICLR 2024Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
40. ICLR 2024Defining and extracting generalizable interaction primitives from DNNs
41. ICLR 2024Demonstration-Regularized RL
42. ICLR 2024DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING
43. ICLR 2024Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
44. ICLR 2024Detecting Pretraining Data from Large Language Models
45. ICLR 2024Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
46. ICLR 2024DP-SGD Without Clipping: The Lipschitz Neural Network Way
47. ICLR 2024Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
48. ICLR 2024Effective and Efficient Federated Tree Learning on Hybrid Data
49. ICLR 2024Enabling Lanuguage Models to Implicitly Learn Self-Improvement
50. ICLR 2024Eureka: Human-Level Reward Design via Coding Large 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.