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 9 of 92

401. ICLR 2026Early Signs of Steganographic Capabilities in Frontier LLMs
402. ICLR 2026EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
403. ICLR 2026EditLens: Quantifying the Extent of AI Editing in Text
404. ICLR 2026EigenBench: A Comparative Behavioral Measure of Value Alignment
405. ICLR 2026ELEPHANT: Measuring and understanding social sycophancy in LLMs
406. ICLR 2026Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs
407. ICLR 2026Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
408. ICLR 2026Emergent Misalignment is Easy, Narrow Misalignment is Hard
409. ICLR 2026EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models
410. ICLR 2026Enabling Fine-Tuning of Direct Feedback Alignment via Feedback-Weight Matching
411. ICLR 2026Enforcing Axioms for AI Alignment under Loss-Based Rules
412. ICLR 2026Enhancing Image-Conditional Coverage in Segmentation: Adaptive Thresholding via Differentiable Miscoverage Loss
413. ICLR 2026Enhancing Language Model Reasoning with Structured Multi-Level Modeling
414. ICLR 2026Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
415. ICLR 2026Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection
416. ICLR 2026Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning
417. ICLR 2026Escaping Policy Contraction: Contraction-Aware PPO (CaPPO) for Stable Language Model Fine-Tuning
418. ICLR 2026Estimating Worst-Case Frontier Risks of Open-Weight LLMs
419. ICLR 2026Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
420. ICLR 2026EventFlash: Towards Efficient MLLMs for Event-Based Vision
421. ICLR 2026Every Language Model Has a Forgery-Resistant Signature
422. ICLR 2026Evidence for Limited Metacognition in LLMs
423. ICLR 2026Evolution and compression in LLMs: on the emergence of human-aligned categorization
424. ICLR 2026Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking
425. ICLR 2026Expertise Can Be Helpful for Reinforcement Learning-based Macro Placement
426. ICLR 2026ExpGuard: LLM Content Moderation in Specialized Domains
427. ICLR 2026Explainable LLM Unlearning through Reasoning
428. ICLR 2026Exploring the Basin-Like Loss Landscape in Large Language Models
429. ICLR 2026Exponential-Wrapped Mechanisms: Differential Privacy on Hadamard Manifolds Made Practical
430. ICLR 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
431. ICLR 2026Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification
432. ICLR 2026Fair Classification by Direct Intervention on Operating Characteristics
433. ICLR 2026Fair Conformal Classification via Learning Representation-Based Groups
434. ICLR 2026Fair Decision Utility in Human-AI Collaboration: Interpretable Confidence Adjustment for Humans with Cognitive Disparities
435. ICLR 2026Fair Graph Machine Learning under Adversarial Missingness Processes
436. ICLR 2026Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
437. ICLR 2026Fair Policy Aggregation from Standard Policy Optimization
438. ICLR 2026Fairness via Independence: A General Regularization Framework for Machine Learning
439. ICLR 2026Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
440. ICLR 2026FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
441. ICLR 2026Fast and Interpretable Protein Substructure Alignment via Optimal Transport
442. ICLR 2026Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
443. ICLR 2026Federated Learning of Quantile Inference under Local Differential Privacy
444. ICLR 2026Federated Learning with Profile Mapping under Distribution Shifts and Drifts
445. ICLR 2026FedMC: Federated Manifold Calibration
446. ICLR 2026Fewer Weights, More Problems: A Practical Attack on LLM Pruning
447. ICLR 2026Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
448. ICLR 2026Fine-tuning Done Right in Model Editing
449. ICLR 2026Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
450. ICLR 2026FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

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.