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

246 papers, page 3 of 5

101. ICML 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
102. ICML 2024Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
103. ICML 2024Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
104. ICML 2024Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
105. ICML 2024Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs
106. ICML 2024KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations
107. ICML 2024Language Models Represent Beliefs of Self and Others
108. ICML 2024LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
109. ICML 2024Learning and Forgetting Unsafe Examples in Large Language Models
110. ICML 2024Learning Associative Memories with Gradient Descent
111. ICML 2024Learning Decision Trees and Forests with Algorithmic Recourse
112. ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
113. ICML 2024Learning Linear Block Error Correction Codes
114. ICML 2024Learning Modality Knowledge Alignment for Cross-Modality Transfer
115. ICML 2024Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
116. ICML 2024Learning to Remove Cuts in Integer Linear Programming
117. ICML 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)
118. ICML 2024Limited Preference Aided Imitation Learning from Imperfect Demonstrations
119. ICML 2024Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
120. ICML 2024Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
121. ICML 2024Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining
122. ICML 2024MaxMin-RLHF: Alignment with Diverse Human Preferences
123. ICML 2024Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization
124. ICML 2024MGit: A Model Versioning and Management System
125. ICML 2024Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
126. ICML 2024MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation
127. ICML 2024Model Alignment as Prospect Theoretic Optimization
128. ICML 2024Model Assessment and Selection under Temporal Distribution Shift
129. ICML 2024Momentum Particle Maximum Likelihood
130. ICML 2024Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks
131. ICML 2024Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution Strategy
132. ICML 2024MusicRL: Aligning Music Generation to Human Preferences
133. ICML 2024Naive Bayes Classifiers over Missing Data: Decision and Poisoning
134. ICML 2024Nash Learning from Human Feedback
135. ICML 2024Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization
136. ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
137. ICML 2024ODIN: Disentangled Reward Mitigates Hacking in RLHF
138. ICML 2024On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
139. ICML 2024On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity
140. ICML 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Training
141. ICML 2024One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
142. ICML 2024Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
143. ICML 2024Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks
144. ICML 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
145. ICML 2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
146. ICML 2024OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
147. ICML 2024Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors
148. ICML 2024Pairwise Alignment Improves Graph Domain Adaptation
149. ICML 2024PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition
150. ICML 2024PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

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.