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 875 篇，第 10 / 18 页

451. ICML 2024Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
452. ICML 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
453. ICML 2024Promoting External and Internal Equities Under Ex-Ante/Ex-Post Metrics in Online Resource Allocation
454. ICML 2024Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
455. ICML 2024Provably Robust DPO: Aligning Language Models with Noisy Feedback
456. ICML 2024Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization
457. ICML 2024Quality-Diversity with Limited Resources
458. ICML 2024Quantum Algorithms and Lower Bounds for Finite-Sum Optimization
459. ICML 2024QuIP$\#$: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
460. ICML 2024Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
461. ICML 2024Random Scaling and Momentum for Non-smooth Non-convex Optimization
462. ICML 2024Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
463. ICML 2024Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation
464. ICML 2024ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
465. ICML 2024Representation Surgery: Theory and Practice of Affine Steering
466. ICML 2024Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
467. ICML 2024Rethinking Optimization and Architecture for Tiny Language Models
468. ICML 2024Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
469. ICML 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
470. ICML 2024Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
471. ICML 2024RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
472. ICML 2024RLVF: Learning from Verbal Feedback without Overgeneralization
473. ICML 2024Robust Stable Spiking Neural Networks
474. ICML 2024Robustly Learning Single-Index Models via Alignment Sharpness
475. ICML 2024Roping in Uncertainty: Robustness and Regularization in Markov Games
476. ICML 2024Safe and Robust Subgame Exploitation in Imperfect Information Games
477. ICML 2024Safe Exploration in Dose Finding Clinical Trials with Heterogeneous Participants
478. ICML 2024Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
479. ICML 2024Scalable AI Safety via Doubly-Efficient Debate
480. ICML 2024Scaling Exponents Across Parameterizations and Optimizers
481. ICML 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
482. ICML 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
483. ICML 2024SelfIE: Self-Interpretation of Large Language Model Embeddings
484. ICML 2024Simultaneous identification of models and parameters of scientific simulators
485. ICML 2024SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
486. ICML 2024Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence
487. ICML 2024Sobolev Space Regularised Pre Density Models
488. ICML 2024SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity
489. ICML 2024Sparse and Structured Hopfield Networks
490. ICML 2024Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
491. ICML 2024Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models
492. ICML 2024Split-and-Denoise: Protect large language model inference with local differential privacy
493. ICML 2024SqueezeLLM: Dense-and-Sparse Quantization
494. ICML 2024Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations
495. ICML 2024Stacking Deep Set Networks and Pooling by Quantiles
496. ICML 2024STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment
497. ICML 2024StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
498. ICML 2024Symmetry Induces Structure and Constraint of Learning
499. ICML 2024Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
500. ICML 2024Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation

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。