缩放定律论文趋势 2023–2026

数据/模型缩放

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 605 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

缩放定律论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023211417860
20243815331096
202580485617201
202682737815248

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

全部缩放定律论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 605 篇，第 8 / 13 页

  1. ICML 2025Scaling Large Motion Models with Million-Level Human Motions
  2. ICML 2025Scaling Laws for Differentially Private Language Models
  3. ICML 2025Scaling Laws for Floating–Point Quantization Training
  4. ICML 2025Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
  5. ICML 2025Scaling Laws for Pre-training Agents and World Models
  6. ICML 2025Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
  7. ICML 2025Scaling Laws for Upcycling Mixture-of-Experts Language Models
  8. ICML 2025Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
  9. ICML 2025Scaling Probabilistic Circuits via Monarch Matrices
  10. ICML 2025Scaling Sparse Feature Circuits For Studying In-Context Learning
  11. ICML 2025Scaling Trends in Language Model Robustness
  12. ICML 2025Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
  13. ICML 2025TabFlex: Scaling Tabular Learning to Millions with Linear Attention
  14. ICML 2025The Importance of Being Lazy: Scaling Limits of Continual Learning
  15. ICML 2025The Underlying Universal Statistical Structure of Natural Datasets
  16. ICML 2025Transformative or Conservative? Conservation laws for ResNets and Transformers
  17. ICML 2025Value-Based Deep RL Scales Predictably
  18. ICML 2025Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
  19. ICML 2025µnit Scaling: Simple and Scalable FP8 LLM Training
  20. NeurIPS 2025$\mu$PC: Scaling Predictive Coding to 100+ Layer Networks
  21. NeurIPS 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillation
  22. NeurIPS 2025AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
  23. NeurIPS 2025Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
  24. NeurIPS 2025Avoiding exp(R) scaling in RLHF through Preference-based Exploration
  25. NeurIPS 2025BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
  26. NeurIPS 2025Can DPO Learn Diverse Human Values? A Theoretical Scaling Law
  27. NeurIPS 2025Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
  28. NeurIPS 2025Complexity Scaling Laws for Neural Models using Combinatorial Optimization
  29. NeurIPS 2025Compute-Optimal Scaling for Value-Based Deep RL
  30. NeurIPS 2025Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
  31. NeurIPS 2025Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
  32. NeurIPS 2025Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality
  33. NeurIPS 2025Dimension-adapted Momentum Outscales SGD
  34. NeurIPS 2025DISC: Dynamic Decomposition Improves LLM Inference Scaling
  35. NeurIPS 2025Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
  36. NeurIPS 2025E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
  37. NeurIPS 2025Efficiently Scaling LLM Reasoning Programs with Certaindex
  38. NeurIPS 2025Emergence and scaling laws in SGD learning of shallow neural networks
  39. NeurIPS 2025Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
  40. NeurIPS 2025Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules
  41. NeurIPS 2025Gemstones: A Model Suite for Multi-Faceted Scaling Laws
  42. NeurIPS 2025GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
  43. NeurIPS 2025GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
  44. NeurIPS 2025HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference
  45. NeurIPS 2025How to Scale Second-Order Optimization
  46. NeurIPS 2025Improved Scaling Laws in Linear Regression via Data Reuse
  47. NeurIPS 2025Inference-Time Hyper-Scaling with KV Cache Compression
  48. NeurIPS 2025Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
  49. NeurIPS 2025Is Limited Participant Diversity Impeding EEG-based Machine Learning?
  50. NeurIPS 2025Kinetics: Rethinking Test-Time Scaling Law

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 查缩放定律在 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": "scaling-laws"}

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缩放定律论文？
共 605 篇，按年份分别是 2023 年 60 篇、2024 年 96 篇、2025 年 201 篇、2026 年 248 篇。
NeurIPS 2026 有多少篇缩放定律论文？
NeurIPS 2026 有 82 篇缩放定律论文，上一届是 80 篇。
ICLR 2026 有多少篇缩放定律论文？
ICLR 2026 有 73 篇缩放定律论文，上一届是 48 篇。
ICML 2026 有多少篇缩放定律论文？
ICML 2026 有 78 篇缩放定律论文，上一届是 56 篇。
CVPR 2026 有多少篇缩放定律论文？
CVPR 2026 有 15 篇缩放定律论文，上一届是 17 篇。
哪个会议的缩放定律论文最多？
NeurIPS，2023–2026 年共 221 篇。

「优化与缩放」下的其他主题