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 7 of 92

301. ICLR 2026BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation
302. ICLR 2026Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
303. ICLR 2026BIRD: Behavior Induction via Representation-structure Distillation
304. ICLR 2026Black-Box Privacy Attacks on Shared Representations in Multitask Learning
305. ICLR 2026Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
306. ICLR 2026BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
307. ICLR 2026Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
308. ICLR 2026Breaking Safety Paradox with Feasible Dual Policy Iteration
309. ICLR 2026Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
310. ICLR 2026Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
311. ICLR 2026Bridging ML and algorithms: comparison of hyperbolic embeddings
312. ICLR 2026Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
313. ICLR 2026Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
314. ICLR 2026CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation
315. ICLR 2026Can LLMs Move Beyond Short Exchanges to Realistic Therapy Conversations?
316. ICLR 2026Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
317. ICLR 2026Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
318. ICLR 2026Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
319. ICLR 2026Can Speech LLMs Think while Listening?
320. ICLR 2026Capability-Based Scaling Trends for LLM-Based Red-Teaming
321. ICLR 2026Cat-PO: Cross-modal Adaptive Token-rewards for Preference Optimization in Truthful Multimodal LLMs
322. ICLR 2026Causal Interpretation of Neural Network Computations with Contribution Decomposition (CODEC)
323. ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
324. ICLR 2026Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach
325. ICLR 2026Change Point Localization and Inference in Dynamic Multilayer Networks
326. ICLR 2026Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
327. ICLR 2026Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
328. ICLR 2026CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
329. ICLR 2026Closing the Modality Gap Aligns Group-Wise Semantics
330. ICLR 2026Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
331. ICLR 2026Co-occurring Associated REtained concepts in Diffusion Unlearning
332. ICLR 2026CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
333. ICLR 2026CodeGenGuard: A Robust Watermark for Code Generation Models
334. ICLR 2026CoFact: Conformal Factuality Guarantees for Language Models under Distribution Shift
335. ICLR 2026CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
336. ICLR 2026COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
337. ICLR 2026Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
338. ICLR 2026Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks
339. ICLR 2026ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types
340. ICLR 2026Consis-GCPO: Consistency-Preserving Group Causal Preference Optimization for Vision Customization
341. ICLR 2026Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models
342. ICLR 2026Constitutional Classifiers++: Production-Grade Defenses against Universal Jailbreaks
343. ICLR 2026ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation
344. ICLR 2026Control Tax: The Price of Keeping AI in Check
345. ICLR 2026Convergence Analysis of Tsetlin Machines under Noise-Free and Noisy Training Conditions: from $2$ Bits to $k$ Bits
346. ICLR 2026Convergent Differential Privacy Analysis for General Federated Learning
347. ICLR 2026Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate
348. ICLR 2026Counterfactual LLM-based Framework for Measuring Rhetorical Style
349. ICLR 2026Critical Confabulation: Can LLMs Hallucinate for Social Good?
350. ICLR 2026Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset

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.