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

623 papers, page 6 of 13

251. ICLR 2026Gradient Intrinsic Dimensionality Alignment：Narrowing The Gap Between Low-Rank Adaptation and Full Fine-Tuning
252. ICLR 2026GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
253. ICLR 2026GradShield: Alignment Preserving Finetuning
254. ICLR 2026GraphShield: Graph-Theoretic Modeling of Network-Level Dynamics for Robust Jailbreak Detection
255. ICLR 2026Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
256. ICLR 2026GuardAlign: Robust Safety Alignment in Multimodal Large Language Models
257. ICLR 2026GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
258. ICLR 2026HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
259. ICLR 2026Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
260. ICLR 2026HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State Correction
261. ICLR 2026Hot PATE: Private Aggregation of Distributions for Diverse Tasks
262. ICLR 2026How Catastrophic is Your LLM? Certifying Risk in Conversation
263. ICLR 2026How Dark Patterns Manipulate Web Agents
264. ICLR 2026How to Square Tensor Networks and Circuits Without Squaring Them
265. ICLR 2026Hubble: a Model Suite to Advance the Study of LLM Memorization
266. ICLR 2026Human-AI Curation Synergy: Scaling Preference Data Curation via Human-Guided AI Feedback
267. ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
268. ICLR 2026Humanline: Online Alignment as Perceptual Loss
269. ICLR 2026IA2: Alignment with ICL Activations improves Supervised Fine-Tuning
270. ICLR 2026ICPO: Provable and Practical In-Context Policy Optimization for Test-Time Scaling
271. ICLR 2026Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
272. ICLR 2026Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization
273. ICLR 2026ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
274. ICLR 2026Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment
275. ICLR 2026In-Context Watermarks for Large Language Models
276. ICLR 2026Incentive-Aligned LLM Summaries
277. ICLR 2026Inconsistency Biases in Dynamic Data Pruning
278. ICLR 2026Inference-Time Personalized Safety Control via Paired Difference-in-Means Intervention
279. ICLR 2026INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
280. ICLR 2026Inoculation Prompting: Eliciting traits from LLMs during training can reduce trait expression at test-time
281. ICLR 2026INTIMA: A Benchmark for Human-AI Companionship Behavior
282. ICLR 2026Intrinsic Explanation of Random Subspace Method for Enhanced Security Applications
283. ICLR 2026Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
284. ICLR 2026Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
285. ICLR 2026Is On-Policy Data always the Best Choice for Direct Preference Optimization-Based LM Alignment?
286. ICLR 2026Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
287. ICLR 2026It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
288. ICLR 2026Jailbreak Transferability Emerges from Shared Representations
289. ICLR 2026Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
290. ICLR 2026Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
291. ICLR 2026JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be Unsafe
292. ICLR 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
293. ICLR 2026JULI: Jailbreak Large Language Models by Self-Introspection
294. ICLR 2026Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
295. ICLR 2026K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
296. ICLR 2026Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization
297. ICLR 2026Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models
298. ICLR 2026Label Smoothing Improves Machine Unlearning
299. ICLR 2026Large Language Model Compression with Global Rank and Sparsity Optimization
300. ICLR 2026Latent Speech-Text Transformer

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.