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 455 篇，第 8 / 10 页

351. NeurIPS 2025Safety Depth in Large Language Models: A Markov Chain Perspective
352. NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
353. NeurIPS 2025SafeVid: Toward Safety Aligned Video Large Multimodal Models
354. NeurIPS 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
355. NeurIPS 2025SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
356. NeurIPS 2025SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
357. NeurIPS 2025Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity
358. NeurIPS 2025Scalable Valuation of Human Feedback through Provably Robust Model Alignment
359. NeurIPS 2025Scaling and context steer LLMs along the same computational path as the human brain
360. NeurIPS 2025Scaling Laws For Scalable Oversight
361. NeurIPS 2025Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
362. NeurIPS 2025SceneForge: Enhancing 3D-text alignment with Structured Scene Compositions
363. NeurIPS 2025scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration
364. NeurIPS 2025SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
365. NeurIPS 2025Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
366. NeurIPS 2025Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
367. NeurIPS 2025Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization
368. NeurIPS 2025Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization
369. NeurIPS 2025Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models
370. NeurIPS 2025Semantic-guided Diverse Decoding for Large Language Model
371. NeurIPS 2025Shape it Up! Restoring LLM Safety during Finetuning
372. NeurIPS 2025Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
373. NeurIPS 2025Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
374. NeurIPS 2025Simple and Efficient Heterogeneous Temporal Graph Neural Network
375. NeurIPS 2025Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
376. NeurIPS 2025SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
377. NeurIPS 2025SkyLadder: Better and Faster Pretraining via Context Window Scheduling
378. NeurIPS 2025SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
379. NeurIPS 2025Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
380. NeurIPS 2025Sparta Alignment: Collectively Aligning Multiple Language Models through Combat
381. NeurIPS 2025Spectral Analysis of Representational Similarity with Limited Neurons
382. NeurIPS 2025Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold
383. NeurIPS 2025Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
384. NeurIPS 2025Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
385. NeurIPS 2025Stable Matching with Ties: Approximation Ratios and Learning
386. NeurIPS 2025Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
387. NeurIPS 2025Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
388. NeurIPS 2025Stop the Nonconsensual Use of Nude Images in Research
389. NeurIPS 2025Storyboard-guided Alignment for Fine-grained Video Action Recognition
390. NeurIPS 2025Strassen Attention, Split VC Dimension and Compositionality in Transformers
391. NeurIPS 2025Strategyproof Reinforcement Learning from Human Feedback
392. NeurIPS 2025STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
393. NeurIPS 2025SuperCLIP: CLIP with Simple Classification Supervision
394. NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
395. NeurIPS 2025Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
396. NeurIPS 2025T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
397. NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent
398. NeurIPS 2025Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
399. NeurIPS 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
400. NeurIPS 2025The Burden of Interactive Alignment with Inconsistent Preferences

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。