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 635 篇，第 7 / 13 页

  1. ICLR 2026Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
  2. ICLR 2026IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
  3. ICLR 2026IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
  4. ICLR 2026IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
  5. ICLR 2026Jacobian Aligned Random Forests
  6. ICLR 2026JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
  7. ICLR 2026JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
  8. ICLR 2026Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
  9. ICLR 2026jqBench: a benchmark for reading and editing JSON from natural language and/or examples
  10. ICLR 2026Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
  11. ICLR 2026KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
  12. ICLR 2026Knowledge Distillation as Decontamination? Revisiting the “Data Laundering” Concern
  13. ICLR 2026KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
  14. ICLR 2026KRAMABENCH: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
  15. ICLR 2026LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis
  16. ICLR 2026Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear Regression
  17. ICLR 2026Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
  18. ICLR 2026Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor–EM Method
  19. ICLR 2026Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
  20. ICLR 2026Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability
  21. ICLR 2026Learning to Interpret Weight Differences in Language Models
  22. ICLR 2026Learning-Augmented Moment Estimation on Time-Decay Models
  23. ICLR 2026LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
  24. ICLR 2026LEXam: Benchmarking Legal Reasoning on 340 Law Exams
  25. ICLR 2026LFQA-E: Carefully Benchmarking Long-form QA Evaluation
  26. ICLR 2026LiveClin: A Live Clinical Benchmark without Leakage
  27. ICLR 2026LiveResearchBench: Benchmarking Single- and Multi-Agent Systems for Citation-Grounded Deep Research
  28. ICLR 2026LiveWeb-IE: A Benchmark For Online Web Information Extraction
  29. ICLR 2026LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena
  30. ICLR 2026LLMs as Rules Oracles: Exploring Real-World Multimodal Reasoning in Tabletop Strategy Game Environments
  31. ICLR 2026LLMs Get Lost In Multi-Turn Conversation
  32. ICLR 2026lmgame-Bench: How Good are LLMs at Playing Games?
  33. ICLR 2026Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification
  34. ICLR 2026LogiConBench: Benchmarking Logical Consistencies of LLMs
  35. ICLR 2026Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism
  36. ICLR 2026Lookup multivariate Kolmogorov-Arnold Networks
  37. ICLR 2026Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?
  38. ICLR 2026M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding
  39. ICLR 2026M4PQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
  40. ICLR 2026ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
  41. ICLR 2026ManipEvalAgent: Promptable and Efficient Evaluation Framework for Robotic Manipulation Policies
  42. ICLR 2026Mapping Overlaps in Benchmarks through Perplexity in the Wild
  43. ICLR 2026MaRS: Memory-Adaptive Routing for Reliable Capacity Expansion and Knowledge Retention
  44. ICLR 2026Matched Data, Better Models: Target Aligned Data Filtering with Sparse Features
  45. ICLR 2026MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
  46. ICLR 2026MCbiF: Measuring Topological Autocorrelation in Multiscale Clusterings via 2-Parameter Persistent Homology
  47. ICLR 2026MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
  48. ICLR 2026MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
  49. ICLR 2026MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
  50. ICLR 2026MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers

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