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 623 篇，第 11 / 13 页

  1. NeurIPS 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
  2. NeurIPS 2026SkipSR: Faster Super-Resolution with Token Skipping
  3. NeurIPS 2026SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang
  4. NeurIPS 2026SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
  5. NeurIPS 2026sMMC-22M: A Context-Aware Dataset and Benchmark for Single-Cell Spatial Transcriptomics
  6. NeurIPS 2026SourceBench: Can AI Answers Reference Quality Web Sources?
  7. NeurIPS 2026Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
  8. NeurIPS 2026Spectral Transformer Neural Processes
  9. NeurIPS 2026Spectral-Spatial Interpretation
  10. NeurIPS 2026Spik-NeRF v2: Pushing the Limit of Spiking Neural Radiance Fields with $ \pm $I-LIF
  11. NeurIPS 2026Spike-SFT: Selective Parameter Enhancement and Fusion for Efficient Spiking Neural Networks
  12. NeurIPS 2026Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks
  13. NeurIPS 2026Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views
  14. NeurIPS 2026Split-RL: Local Conflict Resolution in Reinforcement Learning
  15. NeurIPS 2026Sponsored Questions and How to Auction Them
  16. NeurIPS 2026SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
  17. NeurIPS 2026SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios
  18. NeurIPS 2026Stability-Enhanced Federated Learning with Accelerated Gradient
  19. NeurIPS 2026STAC-R: Subspace-Tracked Activation Compression with Residuals
  20. NeurIPS 2026StarCraft Motion: A Dataset for Agent Simulation in Adversarial and Partially Observable Scenarios
  21. NeurIPS 2026State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
  22. NeurIPS 2026STParOpt: An End-to-End Framework for Execution-Aware Parallelism Inference and Optimized CUDA Migration
  23. NeurIPS 2026Strategic Evaluation: Incentivizing AI Capability Coverage with Private Benchmarks
  24. NeurIPS 2026Strategic Feature Selection and Regularization
  25. NeurIPS 2026Stress-Testing Neural Network Verifiers with Provably Robust Instances
  26. NeurIPS 2026Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency Assessment
  27. NeurIPS 2026Submodular Benchmark Selection
  28. NeurIPS 2026SUPERVISE: A Unified Framework for Standardized and Reproducible Superpixel Evaluation
  29. NeurIPS 2026Surprisingly consistent failures of post-hoc OOD detectors reveal security concerns in open-set recognition with modern CNNs and ViTs, stemming from representation mismatch
  30. NeurIPS 2026SurvCancel: A Longitudinal Dataset and Benchmark for Dynamic Order Cancellation Prediction in On-Demand Ride-Sharing Systems
  31. NeurIPS 2026SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
  32. NeurIPS 2026SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
  33. NeurIPS 2026T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals
  34. NeurIPS 2026TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning
  35. NeurIPS 2026TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
  36. NeurIPS 2026TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
  37. NeurIPS 2026Tactile MNIST: Benchmarking Active Tactile Perception
  38. NeurIPS 2026Temporal Prototype Alignment for Frozen-Feature Dataset Distillation
  39. NeurIPS 2026Tessellations of Semi-Discrete Flow Matching
  40. NeurIPS 2026Test-Time Prompt-Agnostic Decomposition
  41. NeurIPS 2026Testable and Actionable Calibration for Full Swap Regret
  42. NeurIPS 2026Text-to-CAD Evaluation with CADTests
  43. NeurIPS 2026The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest Wildlife
  44. NeurIPS 2026The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
  45. NeurIPS 2026The Bayesian Learning Rule Beyond KL Geometry
  46. NeurIPS 2026The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models
  47. NeurIPS 2026The Deadline Effect: Identifying and Correcting Temporal Bias in Human Evaluation
  48. NeurIPS 2026The Heavy Hitter Oracle: Enhancing Frequency Estimation in Skewed Data Streams
  49. NeurIPS 2026The Illusion of Forgetting: Rank Leakage in Knowledge Editing and Its Mitigation
  50. NeurIPS 2026The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models

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