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 49 of 92

2401. ICLR 2025Self-Boosting Large Language Models with Synthetic Preference Data
2402. ICLR 2025SELF-EVOLVED REWARD LEARNING FOR LLMS
2403. ICLR 2025Self-Improvement in Language Models: The Sharpening Mechanism
2404. ICLR 2025Self-Improving Robust Preference Optimization
2405. ICLR 2025Self-Play Preference Optimization for Language Model Alignment
2406. ICLR 2025Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
2407. ICLR 2025Sensitivity Verification for Additive Decision Tree Ensembles
2408. ICLR 2025SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins
2409. ICLR 2025Severing Spurious Correlations with Data Pruning
2410. ICLR 2025Shape as Line Segments: Accurate and Flexible Implicit Surface Representation
2411. ICLR 2025Shh, don't say that! Domain Certification in LLMs
2412. ICLR 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
2413. ICLR 2025Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype Construction
2414. ICLR 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translation
2415. ICLR 2025SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
2416. ICLR 2025Sparse components distinguish visual pathways & their alignment to neural networks
2417. ICLR 2025Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
2418. ICLR 2025Spurious Forgetting in Continual Learning of Language Models
2419. ICLR 2025Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
2420. ICLR 2025Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
2421. ICLR 2025Strategic Classification With Externalities
2422. ICLR 2025Strong Preferences Affect the Robustness of Preference Models and Value Alignment
2423. ICLR 2025Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
2424. ICLR 2025Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
2425. ICLR 2025SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
2426. ICLR 2025Support is All You Need for Certified VAE Training
2427. ICLR 2025Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
2428. ICLR 2025Tailoring Mixup to Data for Calibration
2429. ICLR 2025Taming Overconfidence in LLMs: Reward Calibration in RLHF
2430. ICLR 2025Tamper-Resistant Safeguards for Open-Weight LLMs
2431. ICLR 2025TASAR: Transfer-based Attack on Skeletal Action Recognition
2432. ICLR 2025Test-time Adaptation for Regression by Subspace Alignment
2433. ICLR 2025Test-time Alignment of Diffusion Models without Reward Over-optimization
2434. ICLR 2025The Crucial Role of Samplers in Online Direct Preference Optimization
2435. ICLR 2025The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
2436. ICLR 2025The Geometry of Categorical and Hierarchical Concepts in Large Language Models
2437. ICLR 2025The Hidden Cost of Waiting for Accurate Predictions
2438. ICLR 2025The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
2439. ICLR 2025The Optimization Landscape of SGD Across the Feature Learning Strength
2440. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
2441. ICLR 2025Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
2442. ICLR 2025TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
2443. ICLR 2025To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation
2444. ICLR 2025To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
2445. ICLR 2025TODO: Enhancing LLM Alignment with Ternary Preferences
2446. ICLR 2025Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
2447. ICLR 2025Towards a learning theory of representation alignment
2448. ICLR 2025Towards Certification of Uncertainty Calibration under Adversarial Attacks
2449. ICLR 2025Towards counterfactual fairness through auxiliary variables
2450. ICLR 2025Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

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.