人工评测论文趋势 2023–2026

主要结论

• 人工评测论文从 2023 年的 33 篇增长到 2026 年的 108 篇，三年间扩大到约 3.3 倍。
• NeurIPS 是发人工评测论文最多的会议，2023–2026 年共 90 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是数据集与基准：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 31 篇。
• 在「评测与基准」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的大模型基准是 154 倍，人工评测是 3.3 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 2026Ad-Hoc Teamwork from Human Demonstrations
• ICML 2026SWE-IF: Aligning Code Evaluation with Human Preference
• ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
• CVPR 2026Bridging Human Evaluation to Infrared and Visible Image Fusion
• NeurIPS 2025Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
• ICML 2025Position: When Incentives Backfire, Data Stops Being Human
• ICLR 2025Eliciting Human Preferences with Language Models
• CVPR 2025DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework
• NeurIPS 2024DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
• ICML 2024A Fine-grained Analysis of Fitted Q-evaluation: Beyond Parametric Models
• ICLR 2024Human Feedback is not Gold Standard
• CVPR 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
• NeurIPS 2023Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?
• ICML 2023Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
• ICLR 2023Beyond calibration: estimating the grouping loss of modern neural networks
• CVPR 20233D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
• NeurIPS 2026AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation
• ICML 2026Rethinking Evaluation Paradigms in IBP-based Certified Training
• ICLR 2026Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
• CVPR 2026Ground Reaction Inertial Poser Physics-based Human Motion Capture from Sparse

全部人工评测论文

共 33 篇，第 1 / 1 页

1. CVPR 20233D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
2. CVPR 20233D Human Mesh Estimation From Virtual Markers
3. CVPR 2023Beyond mAP: Towards Better Evaluation of Instance Segmentation
4. CVPR 2023Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields
5. CVPR 2023GFPose: Learning 3D Human Pose Prior With Gradient Fields
6. CVPR 2023High-Fidelity 3D Human Digitization From Single 2K Resolution Images
7. CVPR 2023Human Pose As Compositional Tokens
8. CVPR 2023HumanGen: Generating Human Radiance Fields With Explicit Priors
9. CVPR 2023Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection
10. CVPR 2023Learning Human Mesh Recovery in 3D Scenes
11. CVPR 2023Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals
12. CVPR 2023Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes
13. CVPR 2023Scene-Aware Egocentric 3D Human Pose Estimation
14. CVPR 2023Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings
15. CVPR 2023Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
16. CVPR 2023UniHCP: A Unified Model for Human-Centric Perceptions
17. CVPR 2023X-Avatar: Expressive Human Avatars
18. ICLR 2023Beyond calibration: estimating the grouping loss of modern neural networks
19. ICLR 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
20. ICLR 2023Human-Guided Fair Classification for Natural Language Processing
21. ICLR 2023Humanly Certifying Superhuman Classifiers
22. ICLR 2023The Role of ImageNet Classes in Fréchet Inception Distance
23. ICLR 2023Words are all you need? Language as an approximation for human similarity judgments
24. ICML 2023Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
25. NeurIPS 2023A Comprehensive Benchmark for Neural Human Radiance Fields
26. NeurIPS 2023Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback
27. NeurIPS 2023Automated Classification of Model Errors on ImageNet
28. NeurIPS 2023Holistic Evaluation of Text-to-Image Models
29. NeurIPS 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
30. NeurIPS 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
31. NeurIPS 2023Off-Policy Evaluation for Human Feedback
32. NeurIPS 2023Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?
33. NeurIPS 2023Statistical Knowledge Assessment for Large Language Models

常见问题

2023–2026 年四大会议一共有多少篇人工评测论文？

共 271 篇，按年份分别是 2023 年 33 篇、2024 年 70 篇、2025 年 60 篇、2026 年 108 篇。

NeurIPS 2026 有多少篇人工评测论文？

NeurIPS 2026 有 39 篇人工评测论文，上一届是 17 篇。

ICLR 2026 有多少篇人工评测论文？

ICLR 2026 有 29 篇人工评测论文，上一届是 16 篇。

ICML 2026 有多少篇人工评测论文？

ICML 2026 有 21 篇人工评测论文，上一届是 14 篇。

CVPR 2026 有多少篇人工评测论文？

CVPR 2026 有 19 篇人工评测论文，上一届是 13 篇。

哪个会议的人工评测论文最多？

NeurIPS，2023–2026 年共 90 篇。