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

551 papers, page 9 of 12

401. ICML 2026RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud Registration
402. ICML 2026Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
403. ICML 2026RLSF-V: Mitigating Hallucinations in MLLMs via Fuzzy Semantic Self-Feedback
404. ICML 2026Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
405. ICML 2026Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment
406. ICML 2026Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
407. ICML 2026Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance
408. ICML 2026Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
409. ICML 2026RSA-CP: Efficient Conformal Prediction in Small-Sample Regimes via Random Score Alignment
410. ICML 2026RSPO: Regularized Self-Play Alignment of Large Language Models
411. ICML 2026SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
412. ICML 2026SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
413. ICML 2026SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
414. ICML 2026SafeSeek: Universal Attribution of Safety Circuits in Language Models
415. ICML 2026SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
416. ICML 2026Safety Alignment of LMs via Non-cooperative Games
417. ICML 2026Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
418. ICML 2026Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
419. ICML 2026Safety-Efficacy Trade Off: Robustness against Data-Poisoning
420. ICML 2026Same Question, Different Lies: Cross-Context Consistency (C³) for Black-Box Sandbagging Detection
421. ICML 2026SARL: Structure-Aligned Reinforcement Learning for Bridging the Perception-Action Gap in Airspace
422. ICML 2026SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
423. ICML 2026Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy
424. ICML 2026Scalable and Interpretable Representation Alignment with Ordinal Similarity
425. ICML 2026scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
426. ICML 2026Securing Multimodal AI through Internal Information Decomposition
427. ICML 2026Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
428. ICML 2026Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
429. ICML 2026Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
430. ICML 2026SEPS: Semantic-Enhanced Patch Slimming Framework for Fine-Grained Cross-Modal Alignment
431. ICML 2026SHARP-Q: Spectral Hessian Alignment and Rectification for Post-training Quantization
432. ICML 2026Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
433. ICML 2026Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
434. ICML 2026SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models
435. ICML 2026SMILE: Extended Deep Submodular Function-Based Instruction and In-context Learning Demonstration Selection
436. ICML 2026Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
437. ICML 2026SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
438. ICML 2026SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance–Diversity Data Selection
439. ICML 2026Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
440. ICML 2026Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
441. ICML 2026Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard
442. ICML 2026Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
443. ICML 2026Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
444. ICML 2026SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
445. ICML 2026Stabilizing PPO via Latent-Space Regularization and KDE-Driven Exploration
446. ICML 2026Stable Spectral Copula Alignment for Robust Multimodal Learning
447. ICML 2026Stable Velocity: A Variance Perspective on Flow Matching
448. ICML 2026Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
449. ICML 2026STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
450. ICML 2026State Space Model with Continuous Limit of HiPPO Matrix: Eigenvalue Analysis and Explicit Solution Formula

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.