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 271 篇，第 1 / 6 页

1. CVPR 2026Beyond Single-View Sufficiency CVBench for Cross-View Human Understanding
2. CVPR 2026Bridging Human Evaluation to Infrared and Visible Image Fusion
3. CVPR 2026Bridging the Perception Gap in Image Super-Resolution Evaluation
4. CVPR 2026CREval An Automated Interpretable Evaluation for Creative Image Manipulation under
5. CVPR 2026Differentially Private 2D Human Pose Estimation
6. CVPR 2026E-comIQ-ZH A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of
7. CVPR 2026Ground Reaction Inertial Poser Physics-based Human Motion Capture from Sparse
8. CVPR 2026Human Geometry Distribution for 3D Animation Generation
9. CVPR 2026HumanVBench Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized
10. CVPR 2026Occluded Human Body Capture with Frequency Domain Denoising Prior
11. CVPR 2026PosterReward Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
12. CVPR 2026Ref4D-VideoBench Four-Dimensional Reference-Based Evaluation of Text-to-Video Generative Models
13. CVPR 2026RHINO Reconstructing Human Interactions with Novel Objects from Monocular Videos
14. CVPR 2026SAM 3D Body Robust Full-Body Human Mesh Recovery
15. CVPR 2026Soul Breathe Life into Digital Human for High-fidelity Long-term Multimodal
16. CVPR 2026Towards Motion Turing Test Evaluating Human-Likeness in Humanoid Robots
17. CVPR 2026UniVBench Towards Unified Evaluation for Video Foundation Models
18. CVPR 2026VideoRealBench A Chain-of-Thought Realism Evaluation Benchmark for Generated Human-Centric Videos
19. CVPR 2026What Are You Doing A Closer Look at Controllable Human
20. ICLR 2026AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
21. ICLR 2026AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators
22. ICLR 2026Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation
23. ICLR 2026Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
24. ICLR 2026CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
25. ICLR 2026Death of the Novel(ty): Beyond N-Gram Novelty as a Metric for Textual Creativity
26. ICLR 2026Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
27. ICLR 2026ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
28. ICLR 2026How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation.
29. ICLR 2026Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction
30. ICLR 2026Human-LLM Collaborative Feature Engineering for Tabular Data
31. ICLR 2026Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models
32. ICLR 2026HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
33. ICLR 2026HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks
34. ICLR 2026LFQA-E: Carefully Benchmarking Long-form QA Evaluation
35. ICLR 2026M4PQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
36. ICLR 2026MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
37. ICLR 2026Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
38. ICLR 2026Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges
39. ICLR 2026Quantum machine learning advantages beyond hardness of evaluation
40. ICLR 2026ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference
41. ICLR 2026Scalable Oversight via Partitioned Human Supervision
42. ICLR 2026SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding
43. ICLR 2026SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification
44. ICLR 2026Systematic Biosafety Evaluation of DNA Language Models under Jailbreak Attacks
45. ICLR 2026The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
46. ICLR 2026The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?
47. ICLR 2026Theory-Grounded Evaluation of Human-Like Fallacy Patterns in LLM Reasoning
48. ICLR 2026Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
49. ICML 2026A Computational Framework for Evaluating Human-likeness in LLMs' Open-ended Human Behaviors
50. ICML 2026AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use

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。