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

4,558 papers, page 8 of 92

351. ICLR 2026Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
352. ICLR 2026D&R: Recovery-based AI-Generated Text Detection via a Single Black-box LLM Call
353. ICLR 2026Data Aware and Scalable Sensitivity Analysis for Decision Tree Ensembles
354. ICLR 2026Data Selection for LLM Alignment Using Fine-Grained Preferences
355. ICLR 2026DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning
356. ICLR 2026Decomposing Extrapolative Problem Solving: Spatial Transfer and Length Scaling with Map Worlds
357. ICLR 2026Decoupling Primitive with Experts: Dynamic Feature Alignment for Compositional Zero-Shot Learning
358. ICLR 2026Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
359. ICLR 2026Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
360. ICLR 2026Defending against Backdoor Attacks via Module Switching
361. ICLR 2026DeRaDiff: Denoising Time Realignment of Diffusion Models
362. ICLR 2026Developmental Federated Tuning: A Cognitive-Inspired Paradigm for Efficient LLM Adaptation
363. ICLR 2026Differentially Private Domain Discovery
364. ICLR 2026DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
365. ICLR 2026Diffusion Alignment as Variataional Expectation-Maximization
366. ICLR 2026Diffusion Negative Preference Optimization Made Simple
367. ICLR 2026Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
368. ICLR 2026Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
369. ICLR 2026Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement
370. ICLR 2026Discrete Diffusion Trajectory Alignment via Stepwise Decomposition
371. ICLR 2026Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling
372. ICLR 2026Disentangling the Factors of Convergence between Brains and Computer Vision Models
373. ICLR 2026Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences
374. ICLR 2026DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment
375. ICLR 2026Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Reasoning Large Language Models
376. ICLR 2026Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
377. ICLR 2026DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration
378. ICLR 2026Do Large Language Models Know What They Are Capable Of?
379. ICLR 2026Don't Forget Its Variance! The Minimum Path Variance Principle for Accurate and Stable Score-Based Models
380. ICLR 2026Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
381. ICLR 2026Doubly-Regressing Approach for Subgroup Fairness
382. ICLR 2026Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas
383. ICLR 2026Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
384. ICLR 2026DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
385. ICLR 2026DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
386. ICLR 2026DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
387. ICLR 2026Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
388. ICLR 2026DrugTrail: Explainable Drug Discovery via Structured Reasoning and Druggability‑Tailored Preference Optimization
389. ICLR 2026Dual Randomized Smoothing: Beyond Global Noise Variance
390. ICLR 2026Dual-Branch Representations with Dynamic Gated Fusion and Triple-Granularity Alignment for Deep Multi-View Clustering
391. ICLR 2026Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation
392. ICLR 2026Dual-Path Condition Alignment for Diffusion Transformers
393. ICLR 2026Dual-Space Smoothness for Robust and Balanced LLM Unlearning
394. ICLR 2026DUET: DISTILLED LLM UNLEARNING FROM AN EFFICIENTLY CONTEXTUALIZED TEACHER
395. ICLR 2026DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
396. ICLR 2026DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
397. ICLR 2026DynaGuard: A Dynamic Guardian Model With User-Defined Policies
398. ICLR 2026Dynamic Reflections: Probing Video Representations with Text Alignment
399. ICLR 2026Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
400. ICLR 2026EAMET: ROBUST MASSIVE MODEL EDITING VIA EMBEDDING ALIGNMENT OPTIMIZATION

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.