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

300 papers, page 6 of 6

251. ICML 2025Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks
252. ICML 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
253. ICML 2025SPRI: Aligning Large Language Models with Context-Situated Principles
254. ICML 2025Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment
255. ICML 2025STAIR: Improving Safety Alignment with Introspective Reasoning
256. ICML 2025Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
257. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
258. ICML 2025Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models
259. ICML 2025SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
260. ICML 2025Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
261. ICML 2025Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
262. ICML 2025TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimization
263. ICML 2025Test-time Correlation Alignment
264. ICML 2025Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
265. ICML 2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
266. ICML 2025The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
267. ICML 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
268. ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
269. ICML 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
270. ICML 2025The Limits of Predicting Agents from Behaviour
271. ICML 2025The Lock-in Hypothesis: Stagnation by Algorithm
272. ICML 2025The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
273. ICML 2025The Missing Alignment Link of In-context Learning on Sequences
274. ICML 2025The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
275. ICML 2025The Relationship Between No-Regret Learning and Online Conformal Prediction
276. ICML 2025Theoretical guarantees on the best-of-n alignment policy
277. ICML 2025Thinking LLMs: General Instruction Following with Thought Generation
278. ICML 2025TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
279. ICML 2025Tokenized Bandit for LLM Decoding and Alignment
280. ICML 2025Topological Signatures of Adversaries in Multimodal Alignments
281. ICML 2025Towards an Explainable Comparison and Alignment of Feature Embeddings
282. ICML 2025Towards Cost-Effective Reward Guided Text Generation
283. ICML 2025Towards Memorization Estimation: Fast, Formal and Free
284. ICML 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
285. ICML 2025Training Deep Learning Models with Norm-Constrained LMOs
286. ICML 2025Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
287. ICML 2025Transformative or Conservative? Conservation laws for ResNets and Transformers
288. ICML 2025TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
289. ICML 2025TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
290. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
291. ICML 2025Unconstrained Robust Online Convex Optimization
292. ICML 2025Understanding High-Dimensional Bayesian Optimization
293. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
294. ICML 2025Understanding the Emergence of Multimodal Representation Alignment
295. ICML 2025Understanding the Logic of Direct Preference Alignment through Logic
296. ICML 2025Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
297. ICML 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
298. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
299. ICML 2025When Can Proxies Improve the Sample Complexity of Preference Learning?
300. ICML 2025When, Where and Why to Average Weights?

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.