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

1,421 papers, page 2 of 29

51. NeurIPS 2026Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria
52. NeurIPS 2026AutoHoney: Automating, Deploying, and Evaluating Scheming Honeypots Across Production Codebases
53. NeurIPS 2026B$^3$-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints
54. NeurIPS 2026BarrierSteer: LLM Safety via Learning Barrier Steering
55. NeurIPS 2026Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
56. NeurIPS 2026BDC-Merge: Cross-Architecture Model Merging via Dependency Alignment
57. NeurIPS 2026BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets
58. NeurIPS 2026Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
59. NeurIPS 2026Bentkus-type asymptotic e-values
60. NeurIPS 2026Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
61. NeurIPS 2026Beyond Pairwise Supervision: Spectral Characteristic Matching for Data-Efficient Multimodal Alignment
62. NeurIPS 2026Beyond Row Alignment: Virtual-Camera-Aware Online Stereo Rectification
63. NeurIPS 2026Beyond Semantic Alignment: Geometric Incomparability in Multi-Oracle Soft Fusion
64. NeurIPS 2026Bias-Variance Optimized Preference Optimization for Large Reasoning Models
65. NeurIPS 2026Bias, Measurement Error, and Double-Dipping: When Can GNN Convolutions Help Brain Connectome Prediction?
66. NeurIPS 2026Bounding Global and Local Compression Error of Signal Parameterizations
67. NeurIPS 2026Bridging Compute- and Data-Optimal Pretraining
68. NeurIPS 2026Bridging Simulation and Reality: Geometry and Decision Alignment for Autonomous Driving
69. NeurIPS 2026Bridging the Simulation-to-Experiment Gap with Adversarial Distribution Alignment
70. NeurIPS 2026BSO: Safety Alignment Is Density Ratio Matching
71. NeurIPS 2026Bug or Feature$^2$: Weight Drift, Activation Sparsity, and Spikes
72. NeurIPS 2026ByteDistill: Cross-Tokenizer Distillation via Chunk-wise Byte-Level Distribution Alignment
73. NeurIPS 2026CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
74. NeurIPS 2026Cauchy Scientific Networks: Loss–Architecture Alignment and Its Limit
75. NeurIPS 2026Causal pieces: analysing and improving spiking neural networks piece by piece
76. NeurIPS 2026Certifiably Optimal Robust Angular Synchronization
77. NeurIPS 2026Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization
78. NeurIPS 2026Chaining 2-FWL GNNs for Combinatorial Graph Alignment
79. NeurIPS 2026CHoRD: Coordinating Scheduling and Data Placement for Efficient Deep Neural Network Inference on Chiplet-Based GPUs
80. NeurIPS 2026Classification at the Edge of Stability: Unifying Self-Stabilization and Convergence Rates
81. NeurIPS 2026Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
82. NeurIPS 2026ClinStab: Stability-Oriented Learning for Medical Time Series via Dual-Stream Alignment
83. NeurIPS 2026Closed-Loop Alignment: Socially Coupled In-Context Learning and Relational Posterior Collapse
84. NeurIPS 2026Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
85. NeurIPS 2026Community-Centered AI is Feasible and Beneficial for Impacted Communities
86. NeurIPS 2026Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
87. NeurIPS 2026Comparing Transformers and Hybrid Models at the Token Level
88. NeurIPS 2026Complex Schrödinger Bridges
89. NeurIPS 2026COMPOSE: Composing Future Theorems from Citations and Formal Structure
90. NeurIPS 2026Computing Thiele Rules on Interval Elections and their Generalizations
91. NeurIPS 2026Concept frustration: Aligning human concepts and machine representations
92. NeurIPS 2026Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates
93. NeurIPS 2026Conservative neural posterior estimation via distributionally robust training
94. NeurIPS 2026Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves
95. NeurIPS 2026Constraint-Aware Influence Estimation in Deep Constrained Learning
96. NeurIPS 2026Correct, Route, Calibrate: Efficient Preference Optimization from Noisy, Heterogeneous Human Feedback
97. NeurIPS 2026Counterfactual Estimation under Composite Treatments via Progressive Distribution Alignment
98. NeurIPS 2026Counterfactual Maps: What They Are and How to Find Them
99. NeurIPS 2026CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment
100. NeurIPS 2026CRAFT: Conflict-Resolved Aggregation for Federated Training

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.