对齐与安全论文趋势 2023–2026

主要结论

• 对齐与安全论文从 2023 年的 438 篇增长到 2026 年的 1,882 篇，三年间扩大到约 4.3 倍。
• NeurIPS 是发对齐与安全论文最多的会议，2023–2026 年共 1,421 篇，占四个会议总量的 31%。
• 交叉方向里涨得最快的是社会层面 · safety：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 137 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的社会层面 · safety是 93 倍，对齐与安全是 4.3 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部对齐与安全论文

共 1,198 篇，第 8 / 24 页

351. ICML 2026Perceptrons and Localization of Attention’s Mean-Field Landscape
352. ICML 2026Personalized Image Generation via Human-in-the-loop Bayesian Optimization
353. ICML 2026PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
354. ICML 2026PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
355. ICML 2026PLANTAIN: Plan-Answer Interleaved Reasoning
356. ICML 2026Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
357. ICML 2026PoMtVRS: Preference-Optimized Multi-Task Vehicle Routing Solver with Preference Gating
358. ICML 2026Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
359. ICML 2026Post-Training Language Models for Crosslingual Consistency
360. ICML 2026Post-Training with Policy Gradients: Optimality and the Base Model Barrier
361. ICML 2026Powerful and Theoretically Guaranteed Independence Testing on Heterogeneous Federated Clients
362. ICML 2026Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
363. ICML 2026Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision
364. ICML 2026Preference-Calibrated Optimization with Score-Level Distribution Alignment for Text-to-Image Diffusion Model Unlearning
365. ICML 2026Preference-Enhanced Reinforcement Learning for Pluralistic Image Inpainting
366. ICML 2026Preference-Modulated Structural Attention for Multi-Objective Combinatorial Optimization
367. ICML 2026Pressure Reveals Character: Behavioural Alignment Evaluation at Depth
368. ICML 2026Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
369. ICML 2026ProMeCD: Unifying Long-Tailed and Noisy Label Learning via White-Box Control
370. ICML 2026Prototype-guided Bilateral Alignment Multimodal Federated Learning
371. ICML 2026Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation
372. ICML 2026PS-PPO : Prefix-Sampling PPO for Critic-Free RLHF
373. ICML 2026QiMeng-PerceptOS: Semantic-Aware Kernel Optimization for OS-Intensive Workloads via Hardware-Software Alignment
374. ICML 2026Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis
375. ICML 2026Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
376. ICML 2026Rare Event Analysis of Large Language Models
377. ICML 2026RBCBF: Decoding Time Safety Alignment via Risk Guided Rollback and Barrier Control
378. ICML 2026Real-Time Aligned Reward Model beyond Semantics
379. ICML 2026REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
380. ICML 2026REAR: Test-time Preference Realignment through Reward Decomposition
381. ICML 2026Reasoning Models Struggle to Control their Chains of Thought
382. ICML 2026Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
383. ICML 2026Recontextualization Mitigates Specification Gaming Without Modifying the Specification
384. ICML 2026RED-HDP-HMM: Observation-Dependent Durations for Bayesian Nonparametric Sequential Models
385. ICML 2026RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
386. ICML 2026Regularized Discriminative Alignment for Deep Representations under Label Shift
387. ICML 2026Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
388. ICML 2026Reliability-Aware LLM Alignment from Inconsistent Human Feedback
389. ICML 2026Reliable Confidence Alignment for Generalized Category Discovery
390. ICML 2026Reliable Neighborhood-Aware Multi-View Outlier Detection
391. ICML 2026Removing Sandbagging in LLMs by Training with Weak Supervision
392. ICML 2026Resilient Coresets and Clustering
393. ICML 2026Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification
394. ICML 2026Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
395. ICML 2026Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
396. ICML 2026Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
397. ICML 2026Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
398. ICML 2026Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios
399. ICML 2026Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
400. ICML 2026Reward-free Alignment for Conflicting Objectives

常见问题

2023–2026 年四大会议一共有多少篇对齐与安全论文？

共 4,558 篇，按年份分别是 2023 年 438 篇、2024 年 875 篇、2025 年 1,363 篇、2026 年 1,882 篇。

NeurIPS 2026 有多少篇对齐与安全论文？

NeurIPS 2026 有 480 篇对齐与安全论文，上一届是 455 篇。

ICLR 2026 有多少篇对齐与安全论文？

ICLR 2026 有 623 篇对齐与安全论文，上一届是 473 篇。

ICML 2026 有多少篇对齐与安全论文？

ICML 2026 有 551 篇对齐与安全论文，上一届是 300 篇。

CVPR 2026 有多少篇对齐与安全论文？

CVPR 2026 有 228 篇对齐与安全论文，上一届是 135 篇。

哪个会议的对齐与安全论文最多？

NeurIPS，2023–2026 年共 1,421 篇。