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 10 / 13 页

  1. NeurIPS 2026Resolution-Aware Structural Density Peak Clustering
  2. NeurIPS 2026Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data
  3. NeurIPS 2026Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
  4. NeurIPS 2026Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
  5. NeurIPS 2026Rethinking Projector Training in Multimodal LLMs
  6. NeurIPS 2026Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
  7. NeurIPS 2026Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
  8. NeurIPS 2026Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity
  9. NeurIPS 2026Reward-Conditioned Reinforcement Learning
  10. NeurIPS 2026Richer or More Gates? Fan-In Trade-offs in Learnable Logic Circuits
  11. NeurIPS 2026RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
  12. NeurIPS 2026Robust and Hard-to-Remove GNN Watermarking via Topological Invariant Perception
  13. NeurIPS 2026Robust Approximate Nearest Neighbor Search for Any Dataset
  14. NeurIPS 2026Robust Domain Generalization under Divergent Marginal and Conditional Distributions
  15. NeurIPS 2026Robust Satisficing Ensemble: Scalable Model Aggregation Under Distribution Shifts
  16. NeurIPS 2026Robust Statistical Estimators with Bounded Empirical Sensitivity
  17. NeurIPS 2026Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection
  18. NeurIPS 2026RSSA: Robust Semantic and Spatial Aligner for Collaborative Perception
  19. NeurIPS 2026RTCBench: Evaluating Tool Use of Large Language Models Beyond Oracle Access
  20. NeurIPS 2026RTEB: An Overfitting-Resistant Benchmark for Embedding Model Evaluation
  21. NeurIPS 2026RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering
  22. NeurIPS 2026S&P: Towards Scalable and Powerful Graph Learning with Hierarchical Structural Acquisition
  23. NeurIPS 2026S3Former: Sequential, Structural, and Statistical Fusion for Continuous-Time Dynamic Graphs
  24. NeurIPS 2026Safe Actions Can Form Unsafe Traces: Benchmarking and Shielding Compositional Emergent Risk in AI Agents
  25. NeurIPS 2026Safe Active Learning with Future Viability Guarantees in Time-Series Models
  26. NeurIPS 2026Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility-Guidance
  27. NeurIPS 2026SafeDrug: A Benchmark Dataset for Safety-Critical Pharmacological Reasoning in LLMs
  28. NeurIPS 2026SAGE: Semantically Disentangled Representation Learning through Latent Geometry Constraint and Large Language Model
  29. NeurIPS 2026SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
  30. NeurIPS 2026Same Words, Different Judgments: How Preferences Vary Across Modalities
  31. NeurIPS 2026SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
  32. NeurIPS 2026Scalable Fair Learning via Cramér-von Mises Regularization
  33. NeurIPS 2026Scaling Arbitrary Architectures and Optimizers with Automatic Parameterization
  34. NeurIPS 2026Scaling Genomic Language Modeling with Unified Corpus and Evaluation in Bacteria
  35. NeurIPS 2026Scaling Point-in-Time Language Models: Economic Evaluation of Embeddings
  36. NeurIPS 2026ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation
  37. NeurIPS 2026Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
  38. NeurIPS 2026Selectivity and Shape in the Design of Forward-Forward Goodness Functions
  39. NeurIPS 2026Self-Evolving Agents Should Build Internal and External Models of the World
  40. NeurIPS 2026Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment
  41. NeurIPS 2026SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
  42. NeurIPS 2026SGD at the Edge of Stability: The Stochastic Sharpness Gap
  43. NeurIPS 2026Sharpness, Stability, and Step-Size Scaling in Deep Polynomial Networks
  44. NeurIPS 2026Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
  45. NeurIPS 2026Short-Context Dominance: How Much Local Context Natural Language Actually Needs?
  46. NeurIPS 2026Simple Baselines are Competitive with Code Evolution
  47. NeurIPS 2026Simplified Reversible Residual Networks
  48. NeurIPS 2026SimSD: Simple Speculative Decoding in Diffusion Language Models
  49. NeurIPS 2026Single-Pass Evidence Measurement for Interpretable and Uncertainty-Aware Multimodal Face Anti-Spoofing
  50. NeurIPS 2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

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