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 26 of 29

1251. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
1252. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
1253. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
1254. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
1255. NeurIPS 2024Unified Lexical Representation for Interpretable Visual-Language Alignment
1256. NeurIPS 2024UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
1257. NeurIPS 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
1258. NeurIPS 2024Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
1259. NeurIPS 2024UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
1260. NeurIPS 2024Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
1261. NeurIPS 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
1262. NeurIPS 2024Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
1263. NeurIPS 2024Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
1264. NeurIPS 2024Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
1265. NeurIPS 2024Verifiably Robust Conformal Prediction
1266. NeurIPS 2024Verified Safe Reinforcement Learning for Neural Network Dynamic Models
1267. NeurIPS 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
1268. NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
1269. NeurIPS 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
1270. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
1271. NeurIPS 2024Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
1272. NeurIPS 2024WeiPer: OOD Detection using Weight Perturbations of Class Projections
1273. NeurIPS 2024What If the Input is Expanded in OOD Detection?
1274. NeurIPS 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
1275. NeurIPS 2024When does perceptual alignment benefit vision representations?
1276. NeurIPS 2024When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
1277. NeurIPS 2024When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
1278. NeurIPS 2024Who's asking? User personas and the mechanics of latent misalignment
1279. NeurIPS 2024WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
1280. NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
1281. NeurIPS 2024Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
1282. NeurIPS 2024Your contrastive learning problem is secretly a distribution alignment problem
1283. NeurIPS 2024ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark
1284. NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
1285. NeurIPS 2023[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
1286. NeurIPS 2023[Re] VAE Approximation Error: ELBO and Exponential Families
1287. NeurIPS 2023A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
1288. NeurIPS 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
1289. NeurIPS 2023A Spectral Theory of Neural Prediction and Alignment
1290. NeurIPS 2023Abide by the law and follow the flow: conservation laws for gradient flows
1291. NeurIPS 2023Alignment with human representations supports robust few-shot learning
1292. NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
1293. NeurIPS 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
1294. NeurIPS 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
1295. NeurIPS 2023Behavior Alignment via Reward Function Optimization
1296. NeurIPS 2023Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
1297. NeurIPS 2023Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment
1298. NeurIPS 2023Bridging Discrete and Backpropagation: Straight-Through and Beyond
1299. NeurIPS 2023Cascading Contextual Assortment Bandits
1300. NeurIPS 2023Closing the gap between the upper bound and lower bound of Adam's iteration complexity

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.