数据集与基准论文趋势 2023–2026

新数据集与评测协议

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,856 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

数据集与基准论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023227162166382937
20244482163183641,346
20256374191893371,582
20266236352754581,991

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

全部数据集与基准论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 337 篇，第 3 / 7 页

  1. CVPR 2025EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection
  2. CVPR 2025ERUPT: Efficient Rendering with Unposed Patch Transformer
  3. CVPR 2025ETAP: Event-based Tracking of Any Point
  4. CVPR 2025Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras
  5. CVPR 2025Extreme Rotation Estimation in the Wild
  6. CVPR 2025F-LMM: Grounding Frozen Large Multimodal Models
  7. CVPR 2025FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs
  8. CVPR 2025Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning
  9. CVPR 2025FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering
  10. CVPR 2025Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
  11. CVPR 2025Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
  12. CVPR 2025Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution
  13. CVPR 2025FoundationStereo: Zero-Shot Stereo Matching
  14. CVPR 2025From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
  15. CVPR 2025FSboard: Over 3 Million Characters of ASL Fingerspelling Collected via Smartphones
  16. CVPR 2025Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes
  17. CVPR 2025GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction
  18. CVPR 2025GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting
  19. CVPR 2025GazeGene: Large-scale Synthetic Gaze Dataset with 3D Eyeball Annotations
  20. CVPR 2025GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency
  21. CVPR 2025GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
  22. CVPR 2025Geometry in Style: 3D Stylization via Surface Normal Deformation
  23. CVPR 2025GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
  24. CVPR 2025GLane3D: Detecting Lanes with Graph of 3D Keypoints
  25. CVPR 2025GOAL: Global-local Object Alignment Learning
  26. CVPR 2025Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
  27. CVPR 2025HandOS: 3D Hand Reconstruction in One Stage
  28. CVPR 2025HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
  29. CVPR 2025Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment
  30. CVPR 2025HD-EPIC: A Highly-Detailed Egocentric Video Dataset
  31. CVPR 2025Hearing Anywhere in Any Environment
  32. CVPR 2025HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
  33. CVPR 2025Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation
  34. CVPR 2025High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm
  35. CVPR 2025HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
  36. CVPR 2025HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views
  37. CVPR 2025How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions
  38. CVPR 2025HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset
  39. CVPR 2025Hybrid Concept Bottleneck Models
  40. CVPR 2025HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
  41. CVPR 2025HyperGS: Hyperspectral 3D Gaussian Splatting
  42. CVPR 2025HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
  43. CVPR 2025Improving Accuracy and Calibration via Differentiated Deep Mutual Learning
  44. CVPR 2025Improving Gaussian Splatting with Localized Points Management
  45. CVPR 2025Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding
  46. CVPR 2025Incremental Object Keypoint Learning
  47. CVPR 2025Insightful Instance Features for 3D Instance Segmentation
  48. CVPR 2025Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline
  49. CVPR 2025Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body
  50. CVPR 2025JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems

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 查数据集与基准在 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": "dataset-and-benchmarks"}

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数据集与基准论文？
共 5,856 篇，按年份分别是 2023 年 937 篇、2024 年 1,346 篇、2025 年 1,582 篇、2026 年 1,991 篇。
NeurIPS 2026 有多少篇数据集与基准论文？
NeurIPS 2026 有 623 篇数据集与基准论文，上一届是 637 篇。
ICLR 2026 有多少篇数据集与基准论文？
ICLR 2026 有 635 篇数据集与基准论文，上一届是 419 篇。
ICML 2026 有多少篇数据集与基准论文？
ICML 2026 有 275 篇数据集与基准论文，上一届是 189 篇。
CVPR 2026 有多少篇数据集与基准论文？
CVPR 2026 有 458 篇数据集与基准论文，上一届是 337 篇。
哪个会议的数据集与基准论文最多？
NeurIPS，2023–2026 年共 1,935 篇。

「效率与系统」下的其他主题