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

348 papers, page 7 of 7

301. NeurIPS 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
302. NeurIPS 2024TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
303. NeurIPS 2024TopoFR: A Closer Look at Topology Alignment on Face Recognition
304. NeurIPS 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
305. NeurIPS 2024Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
306. NeurIPS 2024Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
307. NeurIPS 2024Transfer Q-star : Principled Decoding for LLM Alignment
308. NeurIPS 2024Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
309. NeurIPS 2024Transferable Adversarial Attacks on SAM and Its Downstream Models
310. NeurIPS 2024Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
311. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
312. NeurIPS 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
313. NeurIPS 2024Truth is Universal: Robust Detection of Lies in LLMs
314. NeurIPS 2024UltraMedical: Building Specialized Generalists in Biomedicine
315. NeurIPS 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vector
316. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
317. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
318. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
319. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
320. NeurIPS 2024Unified Lexical Representation for Interpretable Visual-Language Alignment
321. NeurIPS 2024UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
322. NeurIPS 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
323. NeurIPS 2024Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
324. NeurIPS 2024UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
325. NeurIPS 2024Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
326. NeurIPS 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
327. NeurIPS 2024Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
328. NeurIPS 2024Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
329. NeurIPS 2024Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
330. NeurIPS 2024Verifiably Robust Conformal Prediction
331. NeurIPS 2024Verified Safe Reinforcement Learning for Neural Network Dynamic Models
332. NeurIPS 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
333. NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
334. NeurIPS 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
335. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
336. NeurIPS 2024Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
337. NeurIPS 2024WeiPer: OOD Detection using Weight Perturbations of Class Projections
338. NeurIPS 2024What If the Input is Expanded in OOD Detection?
339. NeurIPS 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
340. NeurIPS 2024When does perceptual alignment benefit vision representations?
341. NeurIPS 2024When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
342. NeurIPS 2024When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
343. NeurIPS 2024Who's asking? User personas and the mechanics of latent misalignment
344. NeurIPS 2024WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
345. NeurIPS 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
346. NeurIPS 2024Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
347. NeurIPS 2024Your contrastive learning problem is secretly a distribution alignment problem
348. NeurIPS 2024ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark

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.