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 1,363 篇，第 27 / 28 页

1301. NeurIPS 2025SuperCLIP: CLIP with Simple Classification Supervision
1302. NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
1303. NeurIPS 2025Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
1304. NeurIPS 2025T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
1305. NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent
1306. NeurIPS 2025Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
1307. NeurIPS 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
1308. NeurIPS 2025The Burden of Interactive Alignment with Inconsistent Preferences
1309. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
1310. NeurIPS 2025The emergence of sparse attention: impact of data distribution and benefits of repetition
1311. NeurIPS 2025The Indra Representation Hypothesis
1312. NeurIPS 2025The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
1313. NeurIPS 2025The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 Education
1314. NeurIPS 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
1315. NeurIPS 2025The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
1316. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
1317. NeurIPS 2025Thresholds for sensitive optimality and Blackwell optimality in stochastic games
1318. NeurIPS 2025Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting
1319. NeurIPS 2025Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
1320. NeurIPS 2025Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
1321. NeurIPS 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
1322. NeurIPS 2025Token-Level Self-Play with Importance-Aware Guidance for Large Language Models
1323. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
1324. NeurIPS 2025Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
1325. NeurIPS 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
1326. NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
1327. NeurIPS 2025Training the Untrainable: Introducing Inductive Bias via Representational Alignment
1328. NeurIPS 2025Training-Free Safe Denoisers for Safe Use of Diffusion Models
1329. NeurIPS 2025Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
1330. NeurIPS 2025Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design
1331. NeurIPS 2025TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
1332. NeurIPS 2025Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
1333. NeurIPS 2025U-REPA: Aligning Diffusion U-Nets to ViTs
1334. NeurIPS 2025UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation
1335. NeurIPS 2025Understanding and Rectifying Safety Perception Distortion in VLMs
1336. NeurIPS 2025Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
1337. NeurIPS 2025Unifying Reconstruction and Density Estimation via Invertible Contraction Mapping in One-Class Classification
1338. NeurIPS 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
1339. NeurIPS 2025Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data
1340. NeurIPS 2025Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
1341. NeurIPS 2025Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model
1342. NeurIPS 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
1343. NeurIPS 2025Value Gradient Guidance for Flow Matching Alignment
1344. NeurIPS 2025Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation
1345. NeurIPS 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
1346. NeurIPS 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
1347. NeurIPS 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models
1348. NeurIPS 2025VLMs can Aggregate Scattered Training Patches
1349. NeurIPS 2025VMDT: Decoding the Trustworthiness of Video Foundation Models
1350. NeurIPS 2025VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information

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。