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 1,582 篇，第 14 / 32 页

  1. ICLR 2025Redefining the task of Bioactivity Prediction
  2. ICLR 2025Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs
  3. ICLR 2025Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems
  4. ICLR 2025Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery
  5. ICLR 2025ReSi: A Comprehensive Benchmark for Representational Similarity Measures
  6. ICLR 2025Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance
  7. ICLR 2025Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation
  8. ICLR 2025Revisiting Mode Connectivity in Neural Networks with Bezier Surface
  9. ICLR 2025Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control
  10. ICLR 2025Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating
  11. ICLR 2025RGB-Event ISP: The Dataset and Benchmark
  12. ICLR 2025RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
  13. ICLR 2025RMB: Comprehensively benchmarking reward models in LLM alignment
  14. ICLR 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agents
  15. ICLR 2025Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
  16. ICLR 2025Robustness Auditing for Linear Regression: To Singularity and Beyond
  17. ICLR 2025SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection
  18. ICLR 2025Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
  19. ICLR 2025SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models
  20. ICLR 2025Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
  21. ICLR 2025ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
  22. ICLR 2025SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins
  23. ICLR 2025Shape as Line Segments: Accurate and Flexible Implicit Surface Representation
  24. ICLR 2025Shedding Light on Time Series Classification using Interpretability Gated Networks
  25. ICLR 2025ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents
  26. ICLR 2025Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
  27. ICLR 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
  28. ICLR 2025Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks
  29. ICLR 2025SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark
  30. ICLR 2025Size-Generalizable RNA Structure Evaluation by Exploring Hierarchical Geometries
  31. ICLR 2025Skill Expansion and Composition in Parameter Space
  32. ICLR 2025SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction
  33. ICLR 2025SONICS: Synthetic Or Not - Identifying Counterfeit Songs
  34. ICLR 2025SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
  35. ICLR 2025SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization
  36. ICLR 2025SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
  37. ICLR 2025SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION
  38. ICLR 2025Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
  39. ICLR 2025SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models
  40. ICLR 2025Spreading Out-of-Distribution Detection on Graphs
  41. ICLR 2025Spurious Forgetting in Continual Learning of Language Models
  42. ICLR 2025ST-GCond: Self-supervised and Transferable Graph Dataset Condensation
  43. ICLR 2025Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
  44. ICLR 2025StringLLM: Understanding the String Processing Capability of Large Language Models
  45. ICLR 2025Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models
  46. ICLR 2025Supervised and Semi-Supervised Diffusion Maps with Label-Driven Diffusion
  47. ICLR 2025SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
  48. ICLR 2025SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
  49. ICLR 2025SWEb: A Large Web Dataset for the Scandinavian Languages
  50. ICLR 2025Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

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