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 5 of 10

201. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
202. ICLR 2025How to Evaluate Reward Models for RLHF
203. ICLR 2025How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions
204. ICLR 2025Human-Aligned Chess With a Bit of Search
205. ICLR 2025HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
206. ICLR 2025I Can Hear You: Selective Robust Training for Deepfake Audio Detection
207. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
208. ICLR 2025Improving Data Efficiency via Curating LLM-Driven Rating Systems
209. ICLR 2025Improving Language Model Distillation through Hidden State Matching
210. ICLR 2025Improving Long-Text Alignment for Text-to-Image Diffusion Models
211. ICLR 2025Indirect Gradient Matching for Adversarial Robust Distillation
212. ICLR 2025Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models
213. ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
214. ICLR 2025Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
215. ICLR 2025Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
216. ICLR 2025Interpreting Language Reward Models via Contrastive Explanations
217. ICLR 2025Inverse Constitutional AI: Compressing Preferences into Principles
218. ICLR 2025Is In-Context Learning Sufficient for Instruction Following in LLMs?
219. ICLR 2025Is Your Multimodal Language Model Oversensitive to Safe Queries?
220. ICLR 2025Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision
221. ICLR 2025Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
222. ICLR 2025Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
223. ICLR 2025Jailbreaking as a Reward Misspecification Problem
224. ICLR 2025Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
225. ICLR 2025Joint Graph Rewiring and Feature Denoising via Spectral Resonance
226. ICLR 2025Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment
227. ICLR 2025Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
228. ICLR 2025JudgeLM: Fine-tuned Large Language Models are Scalable Judges
229. ICLR 2025Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
230. ICLR 2025L3Ms — Lagrange Large Language Models
231. ICLR 2025Language Model Alignment in Multilingual Trolley Problems
232. ICLR 2025Language Models are Advanced Anonymizers
233. ICLR 2025Language Models Learn to Mislead Humans via RLHF
234. ICLR 2025Large Language Models can Become Strong Self-Detoxifiers
235. ICLR 2025Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
236. ICLR 2025Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
237. ICLR 2025Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation
238. ICLR 2025LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid
239. ICLR 2025Learn Your Reference Model for Real Good Alignment
240. ICLR 2025Learning and aligning single-neuron invariance manifolds in visual cortex
241. ICLR 2025Learning Causal Alignment for Reliable Disease Diagnosis
242. ICLR 2025Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
243. ICLR 2025Learning Dynamics of LLM Finetuning
244. ICLR 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
245. ICLR 2025Learning from negative feedback, or positive feedback or both
246. ICLR 2025Learning High-Degree Parities: The Crucial Role of the Initialization
247. ICLR 2025Learning LLM-as-a-Judge for Preference Alignment
248. ICLR 2025Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
249. ICLR 2025Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization
250. ICLR 2025LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

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.