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 419 篇，第 6 / 9 页

  1. ICLR 2025MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
  2. ICLR 2025MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation
  3. ICLR 2025MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
  4. ICLR 2025MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
  5. ICLR 2025MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
  6. ICLR 2025Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine
  7. ICLR 2025Multimodal Situational Safety
  8. ICLR 2025MUSE: Machine Unlearning Six-Way Evaluation for Language Models
  9. ICLR 2025N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning
  10. ICLR 2025Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
  11. ICLR 2025Neural Causal Graph for Interpretable and Intervenable Classification
  12. ICLR 2025Neural networks on Symmetric Spaces of Noncompact Type
  13. ICLR 2025New Algorithms for the Learning-Augmented k-means Problem
  14. ICLR 2025NextBestPath: Efficient 3D Mapping of Unseen Environments
  15. ICLR 2025NExUME: Adaptive Training and Inference for DNNs under Intermittent Power Environments
  16. ICLR 2025NL-Eye: Abductive NLI For Images
  17. ICLR 2025No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
  18. ICLR 2025NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
  19. ICLR 2025Number Cookbook: Number Understanding of Language Models and How to Improve It
  20. ICLR 2025OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?
  21. ICLR 2025Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood
  22. ICLR 2025OGBench: Benchmarking Offline Goal-Conditioned RL
  23. ICLR 2025Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models
  24. ICLR 2025OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
  25. ICLR 2025OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
  26. ICLR 2025On a Connection Between Imitation Learning and RLHF
  27. ICLR 2025On Linear Representations and Pretraining Data Frequency in Language Models
  28. ICLR 2025On Stochastic Contextual Bandits with Knapsacks in Small Budget Regime
  29. ICLR 2025On the Byzantine-Resilience of Distillation-Based Federated Learning
  30. ICLR 2025Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics
  31. ICLR 2025OpenHands: An Open Platform for AI Software Developers as Generalist Agents
  32. ICLR 2025OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
  33. ICLR 2025OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
  34. ICLR 2025OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
  35. ICLR 2025Operator Deep Smoothing for Implied Volatility
  36. ICLR 2025OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
  37. ICLR 2025Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
  38. ICLR 2025OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
  39. ICLR 2025Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning
  40. ICLR 2025PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS
  41. ICLR 2025Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities
  42. ICLR 2025Personalized Visual Instruction Tuning
  43. ICLR 2025PersonalLLM: Tailoring LLMs to Individual Preferences
  44. ICLR 2025PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks
  45. ICLR 2025PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
  46. ICLR 2025Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs
  47. ICLR 2025PhysPDE: Rethinking PDE Discovery and a Physical Hypothesis Selection Benchmark
  48. ICLR 2025PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
  49. ICLR 2025PiCO: Peer Review in LLMs based on Consistency Optimization
  50. ICLR 2025Plastic Learning with Deep Fourier Features

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