对齐与安全论文趋势 2023–2026

RLHF、偏好优化、红队与安全对齐

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 4,558 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

对齐与安全论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202313887101112438
2024348156246125875
20254554733001351,363
20264806235512281,882

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

全部对齐与安全论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 4,558 篇，第 68 / 92 页

  1. CVPR 2024Synergistic Global-space Camera and Human Reconstruction from Videos
  2. CVPR 2024SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement
  3. CVPR 2024Targeted Representation Alignment for Open-World Semi-Supervised Learning
  4. CVPR 2024Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis
  5. CVPR 2024Towards Accurate and Robust Architectures via Neural Architecture Search
  6. CVPR 2024Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings
  7. CVPR 2024Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network
  8. CVPR 2024TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light
  9. CVPR 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets
  10. CVPR 2024Unifying Automatic and Interactive Matting with Pretrained ViTs
  11. CVPR 2024Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers
  12. CVPR 2024Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
  13. CVPR 2024Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
  14. CVPR 2024Utility-Fairness Trade-Offs and How to Find Them
  15. CVPR 2024VAREN: Very Accurate and Realistic Equine Network
  16. CVPR 2024VideoCon: Robust Video-Language Alignment via Contrast Captions
  17. CVPR 2024VidLA: Video-Language Alignment at Scale
  18. CVPR 2024VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning
  19. CVPR 2024Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection
  20. CVPR 2024When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach
  21. ICLR 2024#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
  22. ICLR 2024A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
  23. ICLR 2024A unique M-pattern for micro-expression spotting in long videos
  24. ICLR 2024Adversarial Training Should Be Cast as a Non-Zero-Sum Game
  25. ICLR 2024Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
  26. ICLR 2024Aligning Relational Learning with Lipschitz Fairness
  27. ICLR 2024An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment
  28. ICLR 2024An Emulator for Fine-tuning Large Language Models using Small Language Models
  29. ICLR 2024An Investigation of Representation and Allocation Harms in Contrastive Learning
  30. ICLR 2024An Unforgeable Publicly Verifiable Watermark for Large Language Models
  31. ICLR 2024ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
  32. ICLR 2024ARGS: Alignment as Reward-Guided Search
  33. ICLR 2024AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
  34. ICLR 2024Backdoor Contrastive Learning via Bi-level Trigger Optimization
  35. ICLR 2024BadEdit: Backdooring Large Language Models by Model Editing
  36. ICLR 2024Benchmarking and Improving Generator-Validator Consistency of Language Models
  37. ICLR 2024Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
  38. ICLR 2024Beyond Memorization: Violating Privacy via Inference with Large Language Models
  39. ICLR 2024Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
  40. ICLR 2024Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
  41. ICLR 2024Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
  42. ICLR 2024Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
  43. ICLR 2024BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
  44. ICLR 2024Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
  45. ICLR 2024CAS: A Probability-Based Approach for Universal Condition Alignment Score
  46. ICLR 2024Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
  47. ICLR 2024Chain of Hindsight aligns Language Models with Feedback
  48. ICLR 2024Classification with Conceptual Safeguards
  49. ICLR 2024Compositional Preference Models for Aligning LMs
  50. ICLR 2024Compressing LLMs: The Truth is Rarely Pure and Never Simple

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查对齐与安全在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "alignment-and-safety"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「对齐与负责任 AI」下的其他主题