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 1,987 篇，第 39 / 40 页

  1. NeurIPS 2026Tactile MNIST: Benchmarking Active Tactile Perception
  2. NeurIPS 2026Temporal Prototype Alignment for Frozen-Feature Dataset Distillation
  3. NeurIPS 2026Tessellations of Semi-Discrete Flow Matching
  4. NeurIPS 2026Test-Time Prompt-Agnostic Decomposition
  5. NeurIPS 2026Testable and Actionable Calibration for Full Swap Regret
  6. NeurIPS 2026Text-to-CAD Evaluation with CADTests
  7. NeurIPS 2026The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest Wildlife
  8. NeurIPS 2026The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
  9. NeurIPS 2026The Bayesian Learning Rule Beyond KL Geometry
  10. NeurIPS 2026The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models
  11. NeurIPS 2026The Deadline Effect: Identifying and Correcting Temporal Bias in Human Evaluation
  12. NeurIPS 2026The Heavy Hitter Oracle: Enhancing Frequency Estimation in Skewed Data Streams
  13. NeurIPS 2026The Illusion of Forgetting: Rank Leakage in Knowledge Editing and Its Mitigation
  14. NeurIPS 2026The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
  15. NeurIPS 2026The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation
  16. NeurIPS 2026The Marauder’s Map: Bézier Manifolds Reveal Hidden Surfaces for Model Merging and Ensembling
  17. NeurIPS 2026The Path Not Taken: RLVR Learns Off the Principals
  18. NeurIPS 2026The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
  19. NeurIPS 2026The Pok\'emon Theorem and other Fairness Impossibility Results
  20. NeurIPS 2026The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
  21. NeurIPS 2026The Ruler and the Judge: Benchmark-Conditional Evaluation of LLM-as-a-Judge
  22. NeurIPS 2026The Score Kalman Filter
  23. NeurIPS 2026The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
  24. NeurIPS 2026The Sign Code: The Hidden Binary Nature of Deep Networks
  25. NeurIPS 2026The Stability of Data Exchange in Competitive Markets
  26. NeurIPS 2026The Structural Bias of $\ell_2$-Regularized Cross-Entropy Heads in Class-Incremental Learning: Characterization, Limits, and a Gauge-Anchoring Fix
  27. NeurIPS 2026The Subjectivity of Monoculture
  28. NeurIPS 2026The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
  29. NeurIPS 2026THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout
  30. NeurIPS 2026TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
  31. NeurIPS 2026Time series analysis with Gumbel dynamics
  32. NeurIPS 2026TimeWarp: Evaluating Web Agents by Revisiting the Past
  33. NeurIPS 2026Timing Is All You Need: SpikeCore, Learnable Delays, and Gain Control for Neuromorphic Classification
  34. NeurIPS 2026TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs
  35. NeurIPS 2026TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
  36. NeurIPS 2026Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
  37. NeurIPS 2026Toward Multimodal Sheet Music Recognition and Understanding
  38. NeurIPS 2026Towards Identifiable Latent Additive Noise Models
  39. NeurIPS 2026Towards Unified Dynamic Face Landmark Detection
  40. NeurIPS 2026Training Language Models to Explain Their Own Computations
  41. NeurIPS 2026Training-Based Backdoors Are Not Cryptographic
  42. NeurIPS 2026Training-Free 3D Editing via Feature-Divergence Localization and Trajectory Correction
  43. NeurIPS 2026TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
  44. NeurIPS 2026TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering
  45. NeurIPS 2026TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond
  46. NeurIPS 2026TreeWalker: Partial Evaluation for Grouped Tree-Ensemble Inference
  47. NeurIPS 2026TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models
  48. NeurIPS 2026Trivialized Generative Models on Lie Groups
  49. NeurIPS 2026Trustworthy and Efficient Map-free LiDAR Localization via Scan-Pose Alignment and Flow Matching
  50. NeurIPS 2026TSB-SEG: A Systematic Time-Series Segmentation Benchmark

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