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 7 of 12

301. ICML 2026Multilingual Safety Alignment Via Sparse Weight Editing
302. ICML 2026Multimodal Fusion via Self-Consistent Task-Gradient Fields
303. ICML 2026Multimodal Nested Learning for Decoupled and Coordinated Optimization
304. ICML 2026Multimodal Scaling Laws for Task & Data-Optimized Models of Visual Cortex
305. ICML 2026Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
306. ICML 2026N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout
307. ICML 2026Navigating the Pareto Frontier of Alignment: Spectrum-Adaptive Fine-Tuning for LLMs
308. ICML 2026Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0,L_1)$-Smoothness
309. ICML 2026Nested birth-death processes are competitive with neural networks as time-dependent models of protein evolution
310. ICML 2026Neural Logistic Bandits
311. ICML 2026Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
312. ICML 2026Neural-Inspired Modeling of Auditory Selection and Compensation for Audio-Visual Speech Separation
313. ICML 2026NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data
314. ICML 2026NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
315. ICML 2026Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
316. ICML 2026Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
317. ICML 2026Nonparametric Distribution Regression Re-calibration
318. ICML 2026Normalized Rewards for Preference Optimization
319. ICML 2026NorMuon: Making Muon more efficient and scalable
320. ICML 2026Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
321. ICML 2026Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
322. ICML 2026OLion: Approaching the Hadamard Ideal by Intersecting Spectral and L inf Implicit Biases
323. ICML 2026On Densest $k$-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence Analysis
324. ICML 2026On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point Functions
325. ICML 2026On the Convergence of Decentralized Stochastic Minimax Optimization Algorithm with Compressed Communication
326. ICML 2026On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach
327. ICML 2026One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
328. ICML 2026One Probe Won’t Catch Them All: Towards Targeted Deception Detection
329. ICML 2026Online Packet Scheduling with Deadlines and Learning
330. ICML 2026Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection
331. ICML 2026Operationalising the Superficial Alignment Hypothesis via Task Complexity
332. ICML 2026Optimal structure learning and conditional independence testing
333. ICML 2026Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks
334. ICML 2026OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
335. ICML 2026OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
336. ICML 2026OSCS: Online Selection with Provable FAR Control for LLM Safety
337. ICML 2026OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
338. ICML 2026Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
339. ICML 2026Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
340. ICML 2026PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
341. ICML 2026PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic Alignment
342. ICML 2026PADS-TAL: Padding-Annealed Diffusion Sampling in Text-Aware Latent Space for Robust and Diverse Text-to-Music Generation
343. ICML 2026Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series Forecasting
344. ICML 2026Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
345. ICML 2026Pareto-Guided Optimal Transport for Multi-Reward Alignment
346. ICML 2026Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
347. ICML 2026Partial Identification under High-Dimensional Potential Outcomes and Confounders via Optimal Transport
348. ICML 2026Path-conditioned training: a principled way to rescale ReLU neural networks
349. ICML 2026Peer-Preservation in Frontier Models
350. ICML 2026Per-example Gradients: a New Frontier for Understanding and Improving Optimizers

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.