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

4,558 papers, page 45 of 92

2201. ICLR 2025GRAIN: Exact Graph Reconstruction from Gradients
2202. ICLR 2025Gramian Multimodal Representation Learning and Alignment
2203. ICLR 2025Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions
2204. ICLR 2025GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
2205. ICLR 2025Guaranteed Generation from Large Language Models
2206. ICLR 2025Gyrogroup Batch Normalization
2207. ICLR 2025h4rm3l: A Language for Composable Jailbreak Attack Synthesis
2208. ICLR 2025HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS
2209. ICLR 2025HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
2210. ICLR 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
2211. ICLR 2025Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
2212. ICLR 2025HelpSteer2-Preference: Complementing Ratings with Preferences
2213. ICLR 2025HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
2214. ICLR 2025Hessian-Free Online Certified Unlearning
2215. ICLR 2025Higher-Order Graphon Neural Networks: Approximation and Cut Distance
2216. ICLR 2025How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
2217. ICLR 2025How Far Are We from True Unlearnability?
2218. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
2219. ICLR 2025How to Evaluate Reward Models for RLHF
2220. ICLR 2025How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions
2221. ICLR 2025Human-Aligned Chess With a Bit of Search
2222. ICLR 2025HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
2223. ICLR 2025I Can Hear You: Selective Robust Training for Deepfake Audio Detection
2224. ICLR 2025Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
2225. ICLR 2025Improving Data Efficiency via Curating LLM-Driven Rating Systems
2226. ICLR 2025Improving Language Model Distillation through Hidden State Matching
2227. ICLR 2025Improving Long-Text Alignment for Text-to-Image Diffusion Models
2228. ICLR 2025Indirect Gradient Matching for Adversarial Robust Distillation
2229. ICLR 2025Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models
2230. ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
2231. ICLR 2025Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
2232. ICLR 2025Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
2233. ICLR 2025Interpreting Language Reward Models via Contrastive Explanations
2234. ICLR 2025Inverse Constitutional AI: Compressing Preferences into Principles
2235. ICLR 2025Is In-Context Learning Sufficient for Instruction Following in LLMs?
2236. ICLR 2025Is Your Multimodal Language Model Oversensitive to Safe Queries?
2237. ICLR 2025Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision
2238. ICLR 2025Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
2239. ICLR 2025Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
2240. ICLR 2025Jailbreaking as a Reward Misspecification Problem
2241. ICLR 2025Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
2242. ICLR 2025Joint Graph Rewiring and Feature Denoising via Spectral Resonance
2243. ICLR 2025Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment
2244. ICLR 2025Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
2245. ICLR 2025JudgeLM: Fine-tuned Large Language Models are Scalable Judges
2246. ICLR 2025Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
2247. ICLR 2025L3Ms — Lagrange Large Language Models
2248. ICLR 2025Language Model Alignment in Multilingual Trolley Problems
2249. ICLR 2025Language Models are Advanced Anonymizers
2250. ICLR 2025Language Models Learn to Mislead Humans via RLHF

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.