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 7 of 29

301. NeurIPS 2026PortPy: A Benchmark for AI and Optimization in Cancer Radiotherapy Planning
302. NeurIPS 2026PoSafeNet: Structured Safety Learning via Compositional Projection
303. NeurIPS 2026Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent
304. NeurIPS 2026Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
305. NeurIPS 2026Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
306. NeurIPS 2026Post-hoc Selective Classification for Reliable Synthetic Image Detection
307. NeurIPS 2026Prediction-Intervention Games and Invariant Sets
308. NeurIPS 2026Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
309. NeurIPS 2026Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving
310. NeurIPS 2026Pretraining Curricula Enable Selective Fine-tuning
311. NeurIPS 2026Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
312. NeurIPS 2026PRISM: Phenotype-Resolved Inference in Single-Cell Mixed Models via Latent Disease States and Contextualized Differential Expression
313. NeurIPS 2026PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
314. NeurIPS 2026PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning
315. NeurIPS 2026PRISMIC: Reconstructing User Preference via Intent Decomposition and Consolidation
316. NeurIPS 2026PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
317. NeurIPS 2026ProAlign: Progressive Positional and Prototype-Guided Alignment for Aerial-Ground Person Re-Identification
318. NeurIPS 2026PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
319. NeurIPS 2026ProjKAN: Model Compression via KAN Projections to Bridge the Hypothesis and Capacity Gaps
320. NeurIPS 2026ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
321. NeurIPS 2026Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
322. NeurIPS 2026Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
323. NeurIPS 2026RADAR: Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations
324. NeurIPS 2026RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
325. NeurIPS 2026RealityTest: How People Probe AI Identity and Whether Models Disclose It
326. NeurIPS 2026Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
327. NeurIPS 2026Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning
328. NeurIPS 2026ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
329. NeurIPS 2026Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
330. NeurIPS 2026Region-Normalized DPO for Medical Image Segmentation
331. NeurIPS 2026Reliable Clustering and Quantization via Distortion-Constrained Optimal Transport
332. NeurIPS 2026Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
333. NeurIPS 2026RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository Documentation
334. NeurIPS 2026Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
335. NeurIPS 2026Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
336. NeurIPS 2026Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
337. NeurIPS 2026Resolution-Aware Structural Density Peak Clustering
338. NeurIPS 2026Rethinking CT Synthesis through Semantics-Structure Alignment
339. NeurIPS 2026Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
340. NeurIPS 2026Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking Models
341. NeurIPS 2026Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
342. NeurIPS 2026Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
343. NeurIPS 2026Rethinking Sequential Locate-Then-Edit: Optimality and Stability
344. NeurIPS 2026Revisiting Decentralized Online Convex Optimization with Compressed Communication
345. NeurIPS 2026Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity
346. NeurIPS 2026Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions
347. NeurIPS 2026RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
348. NeurIPS 2026Risk-Sensitive Deep Optimal Stopping
349. NeurIPS 2026RL-Inf: Tracking Non-local Training Data Influence for Online Reinforcement Learning
350. NeurIPS 2026Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration

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.