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

1,339 papers, page 2 of 27

51. ICLR 2026AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
52. ICLR 2026Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
53. ICLR 2026Balancing the Experts: Unlocking LoRA-MoE for GRPO via Mechanism-Aware Rewards
54. ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
55. ICLR 2026BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
56. ICLR 2026BaseReward: A Strong Baseline for Multimodal Reward Model
57. ICLR 2026Batch and Sequential Unlearning for Neural Networks
58. ICLR 2026Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
59. ICLR 2026Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
60. ICLR 2026Benchmarking Open-ended Segmentation
61. ICLR 2026Benchmarking Overton Pluralism in LLMs
62. ICLR 2026Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
63. ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
64. ICLR 2026Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
65. ICLR 2026Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
66. ICLR 2026Beyond Pairwise: Empowering LLM Alignment With (Ranked) Choice Modeling
67. ICLR 2026Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
68. ICLR 2026Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
69. ICLR 2026Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
70. ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
71. ICLR 2026Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
72. ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
73. ICLR 2026BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation
74. ICLR 2026Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
75. ICLR 2026BIRD: Behavior Induction via Representation-structure Distillation
76. ICLR 2026Black-Box Privacy Attacks on Shared Representations in Multitask Learning
77. ICLR 2026Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
78. ICLR 2026BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
79. ICLR 2026Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
80. ICLR 2026Breaking Safety Paradox with Feasible Dual Policy Iteration
81. ICLR 2026Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
82. ICLR 2026Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
83. ICLR 2026Bridging ML and algorithms: comparison of hyperbolic embeddings
84. ICLR 2026Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
85. ICLR 2026Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
86. ICLR 2026CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation
87. ICLR 2026Can LLMs Move Beyond Short Exchanges to Realistic Therapy Conversations?
88. ICLR 2026Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
89. ICLR 2026Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
90. ICLR 2026Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
91. ICLR 2026Can Speech LLMs Think while Listening?
92. ICLR 2026Capability-Based Scaling Trends for LLM-Based Red-Teaming
93. ICLR 2026Cat-PO: Cross-modal Adaptive Token-rewards for Preference Optimization in Truthful Multimodal LLMs
94. ICLR 2026Causal Interpretation of Neural Network Computations with Contribution Decomposition (CODEC)
95. ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
96. ICLR 2026Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach
97. ICLR 2026Change Point Localization and Inference in Dynamic Multilayer Networks
98. ICLR 2026Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
99. ICLR 2026Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
100. ICLR 2026CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives

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.