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 4 of 29

151. NeurIPS 2026Fast and slow gradient descent dynamics of logistic regression through weak alignment
152. NeurIPS 2026Fast Approximate $\ell_p$ Chamfer Distance via Lopsided Embeddings and Structured JL
153. NeurIPS 2026Fault Tolerance in Transformers Favors Output Alignment over Hidden-State Consistency
154. NeurIPS 2026Fed-AGA: An Anchor Graph Alignment Framework for Federated Unaligned Multi-view Clustering
155. NeurIPS 2026Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
156. NeurIPS 2026Feeling of Knowing in Large Language Models
157. NeurIPS 2026Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
158. NeurIPS 2026Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
159. NeurIPS 2026Fine-tuning Does Not Reach All: Uneven Safety and Knowledge Dynamics in Language Models
160. NeurIPS 2026FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping
161. NeurIPS 2026FLIP: Fast and Accurate Global Lipschitz Estimation for Large Feedforward Networks
162. NeurIPS 2026FOAM: Factored One-sided Adam-Moment for Practical and Scalable SOAP
163. NeurIPS 2026FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification
164. NeurIPS 2026Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
165. NeurIPS 2026From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability
166. NeurIPS 2026From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
167. NeurIPS 2026From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment
168. NeurIPS 2026From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation
169. NeurIPS 2026From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
170. NeurIPS 2026Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
171. NeurIPS 2026GCD: Correcting Hidden-State Bias in Off-Policy Agentic RL
172. NeurIPS 2026GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
173. NeurIPS 2026GEM: Interpretable Language Models via Geometric Embedding Alignment
174. NeurIPS 2026Generalized Adaptive Boosting and the Geometry of Mistakes
175. NeurIPS 2026Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap
176. NeurIPS 2026Geometry-Aware Directional Alignment for Coherent Model Merging
177. NeurIPS 2026Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
178. NeurIPS 2026Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
179. NeurIPS 2026Gradient Descent on Two ReLU Neurons: Global Landscape and Bifurcation Dynamics
180. NeurIPS 2026Gradient Descent’s Last Iterate is Often (slightly) Suboptimal
181. NeurIPS 2026GradShield: Alignment Preserving Finetuning
182. NeurIPS 2026GradTrack: Detecting Noisy Labels via Temporal Trajectories of Class-wise Gradient Misalignment
183. NeurIPS 2026Graph Label Alignment: A Diagnostic Atlas for Graph Classification
184. NeurIPS 2026Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
185. NeurIPS 2026Greedy Alignment Principle for Optimizer Selection
186. NeurIPS 2026GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
187. NeurIPS 2026Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
188. NeurIPS 2026Hallucination-Guided Unlearning: Using Hallucination Traces to Reveal Overfitted Memories
189. NeurIPS 2026HARC: Coupling Harmfulness and Refusal Capabilities for Robust Safety Alignment
190. NeurIPS 2026Harnessing Textual Refusal Directions for Multimodal Safety
191. NeurIPS 2026HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
192. NeurIPS 2026Hierarchical Cross-Class Part Alignment for Prototypical Part Networks via Hyperbolic Entailment
193. NeurIPS 2026Hierarchical Graph Alignment for Cross-Modal 3D Scene Grounding
194. NeurIPS 2026HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields
195. NeurIPS 2026Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
196. NeurIPS 2026Hyperagents
197. NeurIPS 2026Identification and Bounding of Joint Expectation over Potential Outcomes
198. NeurIPS 2026Improved State Mixing in Higher-order and Block Diagonal Linear Recurrent Networks
199. NeurIPS 2026Improving Audit Realism with Inference-Time Compute and Deployment Scaffolds
200. NeurIPS 2026Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models

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.