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

1,363 papers, page 7 of 28

301. ICLR 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
302. ICLR 2025Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
303. ICLR 2025Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
304. ICLR 2025Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration
305. ICLR 2025FormalAlign: Automated Alignment Evaluation for Autoformalization
306. ICLR 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
307. ICLR 2025From Search to Sampling: Generative Models for Robust Algorithmic Recourse
308. ICLR 2025Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
309. ICLR 2025Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation
310. ICLR 2025GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
311. ICLR 2025Generalization and Distributed Learning of GFlowNets
312. ICLR 2025Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
313. ICLR 2025Generative Classifiers Avoid Shortcut Solutions
314. ICLR 2025Generative Monoculture in Large Language Models
315. ICLR 2025Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
316. ICLR 2025Global Identifiability of Overcomplete Dictionary Learning via L1 and Volume Minimization
317. ICLR 2025GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring
318. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
319. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
320. ICLR 2025Gramian Multimodal Representation Learning and Alignment
321. ICLR 2025Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions
322. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
323. ICLR 2025Guaranteed Generation from Large Language Models
324. ICLR 2025Gyrogroup Batch Normalization
325. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
326. ICLR 2025HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS
327. ICLR 2025HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
328. ICLR 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
329. ICLR 2025Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
330. ICLR 2025HelpSteer2-Preference: Complementing Ratings with Preferences
331. ICLR 2025HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
332. ICLR 2025Hessian-Free Online Certified Unlearning
333. ICLR 2025Higher-Order Graphon Neural Networks: Approximation and Cut Distance
334. ICLR 2025How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
335. ICLR 2025How Far Are We from True Unlearnability?
336. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
337. ICLR 2025How to Evaluate Reward Models for RLHF
338. ICLR 2025How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions
339. ICLR 2025Human-Aligned Chess With a Bit of Search
340. ICLR 2025HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
341. ICLR 2025I Can Hear You: Selective Robust Training for Deepfake Audio Detection
342. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
343. ICLR 2025Improving Data Efficiency via Curating LLM-Driven Rating Systems
344. ICLR 2025Improving Language Model Distillation through Hidden State Matching
345. ICLR 2025Improving Long-Text Alignment for Text-to-Image Diffusion Models
346. ICLR 2025Indirect Gradient Matching for Adversarial Robust Distillation
347. ICLR 2025Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models
348. ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
349. ICLR 2025Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
350. ICLR 2025Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

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.