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

455 papers, page 7 of 10

301. NeurIPS 2025Position: Require Frontier AI Labs To Release Small "Analog" Models
302. NeurIPS 2025Position: Towards Bidirectional Human-AI Alignment
303. NeurIPS 2025Pre-Trained Policy Discriminators are General Reward Models
304. NeurIPS 2025Predictive Preference Learning from Human Interventions
305. NeurIPS 2025Preference Distillation via Value based Reinforcement Learning
306. NeurIPS 2025Preference Learning with Lie Detectors can Induce Honesty or Evasion
307. NeurIPS 2025Preference Learning with Response Time: Robust Losses and Guarantees
308. NeurIPS 2025Preference Optimization by Estimating the Ratio of the Data Distribution
309. NeurIPS 2025Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
310. NeurIPS 2025Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
311. NeurIPS 2025Prior Forgetting and In-Context Overfitting
312. NeurIPS 2025Probabilistic Stability Guarantees for Feature Attributions
313. NeurIPS 2025Probabilistic Token Alignment for Large Language Model Fusion
314. NeurIPS 2025Prohibiting Generative AI in any Form of Weapon Control
315. NeurIPS 2025Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a Restorer
316. NeurIPS 2025Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
317. NeurIPS 2025Protein Inverse Folding From Structure Feedback
318. NeurIPS 2025Provably Efficient Online RLHF with One-Pass Reward Modeling
319. NeurIPS 2025Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO
320. NeurIPS 2025PurpCode: Reasoning for Safer Code Generation
321. NeurIPS 2025Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers
322. NeurIPS 2025Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
323. NeurIPS 2025Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
324. NeurIPS 2025Real-DRL: Teach and Learn in Reality
325. NeurIPS 2025Reasoning as an Adaptive Defense for Safety
326. NeurIPS 2025Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
327. NeurIPS 2025Reconstruction and Secrecy under Approximate Distance Queries
328. NeurIPS 2025Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
329. NeurIPS 2025Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
330. NeurIPS 2025Refusal Direction is Universal Across Safety-Aligned Languages
331. NeurIPS 2025Reinforcement Learning with Backtracking Feedback
332. NeurIPS 2025Reliably detecting model failures in deployment without labels
333. NeurIPS 2025RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models
334. NeurIPS 2025ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
335. NeurIPS 2025RePO: Understanding Preference Learning Through ReLU-Based Optimization
336. NeurIPS 2025Residual Stream Analysis of Overfitting And Structural Disruptions
337. NeurIPS 2025ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
338. NeurIPS 2025RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
339. NeurIPS 2025Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
340. NeurIPS 2025Risk-aware Direct Preference Optimization under Nested Risk Measure
341. NeurIPS 2025Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding
342. NeurIPS 2025Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
343. NeurIPS 2025Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
344. NeurIPS 2025RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
345. NeurIPS 2025RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
346. NeurIPS 2025SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
347. NeurIPS 2025Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
348. NeurIPS 2025Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
349. NeurIPS 2025SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
350. NeurIPS 2025SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism

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.