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 7 of 10

301. ICLR 2025On the Adversarial Vulnerability of Label-Free Test-Time Adaptation
302. ICLR 2025On the Hölder Stability of Multiset and Graph Neural Networks
303. ICLR 2025On the Price of Differential Privacy for Hierarchical Clustering
304. ICLR 2025On the Role of Attention Heads in Large Language Model Safety
305. ICLR 2025On-the-fly Preference Alignment via Principle-Guided Decoding
306. ICLR 2025One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment
307. ICLR 2025Online Preference Alignment for Language Models via Count-based Exploration
308. ICLR 2025Online-to-Offline RL for Agent Alignment
309. ICLR 2025Pacmann: Efficient Private Approximate Nearest Neighbor Search
310. ICLR 2025PAD: Personalized Alignment of LLMs at Decoding-time
311. ICLR 2025Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning
312. ICLR 2025PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment
313. ICLR 2025PaLD: Detection of Text Partially Written by Large Language Models
314. ICLR 2025Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
315. ICLR 2025Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
316. ICLR 2025Persistent Pre-training Poisoning of LLMs
317. ICLR 2025Personality Alignment of Large Language Models
318. ICLR 2025PersonalLLM: Tailoring LLMs to Individual Preferences
319. ICLR 2025PFGuard: A Generative Framework with Privacy and Fairness Safeguards
320. ICLR 2025PiCO: Peer Review in LLMs based on Consistency Optimization
321. ICLR 2025Plastic Learning with Deep Fourier Features
322. ICLR 2025Policy Design in Long-run Welfare Dynamics
323. ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias
324. ICLR 2025Preference Diffusion for Recommendation
325. ICLR 2025Preference Optimization for Reasoning with Pseudo Feedback
326. ICLR 2025Privacy Auditing of Large Language Models
327. ICLR 2025Privately Counting Partially Ordered Data
328. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
329. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
330. ICLR 2025Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution
331. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
332. ICLR 2025Programming Refusal with Conditional Activation Steering
333. ICLR 2025Prompting Fairness: Integrating Causality to Debias Large Language Models
334. ICLR 2025ProtoSnap: Prototype Alignment For Cuneiform Signs
335. ICLR 2025Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
336. ICLR 2025Provable weak-to-strong generalization via benign overfitting
337. ICLR 2025Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
338. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
339. ICLR 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples
340. ICLR 2025Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
341. ICLR 2025QA-Calibration of Language Model Confidence Scores
342. ICLR 2025QPM: Discrete Optimization for Globally Interpretable Image Classification
343. ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
344. ICLR 2025Reassessing How to Compare and Improve the Calibration of Machine Learning Models
345. ICLR 2025Reconciling Model Multiplicity for Downstream Decision Making
346. ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
347. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
348. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
349. ICLR 2025Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
350. ICLR 2025Regretful Decisions under Label Noise

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.