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 2 of 12

51. ICML 2026BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
52. ICML 2026BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AI
53. ICML 2026Breaking the Reference Bottleneck via Learning to Rewrite Conversational Queries without Gold Reference Passages
54. ICML 2026Brep2Shape: Boundary and Shape Representation Alignment via Self-supervised Transformers
55. ICML 2026Bridging Spherical Black-Box Optimizers
56. ICML 2026Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
57. ICML 2026BroRL: Scaling Reinforcement Learning via Broadened Exploration
58. ICML 2026Calibrated Preference Learning: The Case of Label Ranking
59. ICML 2026Calibrating Conservatism for Scalable Oversight
60. ICML 2026CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
61. ICML 2026CAMP: Coherent Alignment of Multimodal Prototypes for Explainable Complementary Learning
62. ICML 2026Can VLMs Diagnose and Recover from VLA Manipulation Faults?
63. ICML 2026Capability Traps in DPO
64. ICML 2026Capacity without Access: Reinterpreting the Mid-Depth Spectral Plateau in LLMs
65. ICML 2026CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization
66. ICML 2026CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
67. ICML 2026Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
68. ICML 2026Causes and Consequences of Representational Similarity in Machine Learning Models
69. ICML 2026Certificate-Guided Pruning for Stochastic Lipschitz Optimization
70. ICML 2026Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
71. ICML 2026CL-GCL: Comprehensive and Lightweight Graph Contrastive Learning
72. ICML 2026Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
73. ICML 2026ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education
74. ICML 2026Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
75. ICML 2026Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
76. ICML 2026Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
77. ICML 2026CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
78. ICML 2026Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
79. ICML 2026Compact Conformal Subgraphs
80. ICML 2026Compressed Sensing for Capability Localization in Large Language Models
81. ICML 2026Concept Concentration for Faithful Representation Intervention
82. ICML 2026Concept Heterogeneity-aware Representation Steering
83. ICML 2026Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling
84. ICML 2026Conditional Equivalence of DPO and RLHF: Assumptions, Failure Modes, and Provable Alignment
85. ICML 2026Configurable Reward Model for Balanced Safety Alignment
86. ICML 2026Conflict-Aware Adaptive Alignment for LLM Hallucination Mitigation
87. ICML 2026Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
88. ICML 2026Conformal Policy Control
89. ICML 2026Conformal Prediction for Early Stopping in Mixed Integer Optimization
90. ICML 2026Conformal Risk-Averse Decision Making with Action Conditional Guarantee
91. ICML 2026Consistency Training Can Entrench Misalignment
92. ICML 2026Constitutional Black-Box Monitoring for Scheming in LLM Agents
93. ICML 2026Contextual Slate GLM Bandits with Limited Adaptivity
94. ICML 2026Contrastive Weak-to-Strong Generalization
95. ICML 2026Controllable and Explainable Personality Sliders for LLMs at Inference Time
96. ICML 2026Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
97. ICML 2026Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning
98. ICML 2026Convergent World Representations and Divergent Tasks
99. ICML 2026Convex Optimization for Alignment and Preference Learning on a Single GPU
100. ICML 2026Copyright-Bench: Agentic Evaluation of Copyright Law Compliance

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.