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

1,882 papers, page 33 of 38

1601. NeurIPS 2026Improving Audit Realism with Inference-Time Compute and Deployment Scaffolds
1602. NeurIPS 2026Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models
1603. NeurIPS 2026Inference Time Nash Alignment
1604. NeurIPS 2026Inference-time Alignment via Sparse Junction Steering
1605. NeurIPS 2026Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
1606. NeurIPS 2026Instance-Dependent Bandit Convex Optimization in One Dimension
1607. NeurIPS 2026Internal Safety Collapse in Frontier Large Language Models
1608. NeurIPS 2026Interpretable Multiway-Split Trees
1609. NeurIPS 2026Intersectional Fairness via Mixed-Integer Optimization
1610. NeurIPS 2026Introspective Coupling: LMs Learn to Explain Themselves Better Than Their Training Targets
1611. NeurIPS 2026Invariance and Body-Order Compose Additively: Minimax Rates on $\mathrm{SO}(3)^n$
1612. NeurIPS 2026ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining
1613. NeurIPS 2026JailBound: A FOL-Guided Jailbreak Evaluation Framework for Revealing Safety Boundaries of LLMs
1614. NeurIPS 2026Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
1615. NeurIPS 2026Jointly Robust Fairness: Overcoming Simultaneous Label and Attribute Noise
1616. NeurIPS 2026JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment
1617. NeurIPS 2026L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark
1618. NeurIPS 2026Latency-Conditioned Selection Bias in RLHF
1619. NeurIPS 2026Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation
1620. NeurIPS 2026Learning Data-free Universal Adversarial Perturbation with Hybrid Priors and Gradient-Guided Sharpness Regularization
1621. NeurIPS 2026Learning How to Cube
1622. NeurIPS 2026Learning Rate Transfer in Normalized Transformers
1623. NeurIPS 2026Learning to Decide with AI Assistance under Human-Alignment
1624. NeurIPS 2026Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling
1625. NeurIPS 2026Leviathan: Decoupling Input and Output Representations in Language Models
1626. NeurIPS 2026Limits and Potential of Score-Based Data Valuation: Redundancy, Complementarity, and Non-Monotonicity
1627. NeurIPS 2026LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
1628. NeurIPS 2026Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models
1629. NeurIPS 2026LLM Active Alignment: A Nash Equilibrium Perspective
1630. NeurIPS 2026LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
1631. NeurIPS 2026Local Sparsity Enables Unsupervised LLM Safety Detection
1632. NeurIPS 2026Localizing and Repairing Sparse-Prompt Failure in SAM Decoders via Box-to-Point Counterfactual
1633. NeurIPS 2026Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
1634. NeurIPS 2026Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation
1635. NeurIPS 2026Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits
1636. NeurIPS 2026LoopWeaver: Weaving Feedback Loops into Hierarchical Generation under Constraints
1637. NeurIPS 2026LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
1638. NeurIPS 2026Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
1639. NeurIPS 2026LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
1640. NeurIPS 2026Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
1641. NeurIPS 2026Manifold-weighted neural networks
1642. NeurIPS 2026MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
1643. NeurIPS 2026MAPS: Margin-Aware Priors and Verifier-Guided Search for Embodied Planning
1644. NeurIPS 2026Margin Dynamics for Large Language Model Alignment
1645. NeurIPS 2026Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
1646. NeurIPS 2026Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment
1647. NeurIPS 2026MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
1648. NeurIPS 2026Matryoshka Transcoders and Hierarchy Misalignment: When SAE Absorption Protection Does Not Transfer
1649. NeurIPS 2026MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
1650. NeurIPS 2026Merging RLVR-Trained Experts via Policy-Shift-Guided Spectral Alignment

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.