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 248 篇，第 4 / 5 页

  1. ICML 2026Selling Data as a Digital Good with Scaling Valuations
  2. ICML 2026Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
  3. ICML 2026Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
  4. ICML 2026Statistically Calibrated Scaling for Token Merging in Transformers
  5. ICML 2026Temperature Scaling in Discrete Sequence (Language) Models
  6. ICML 2026Token Sample Complexity of Attention
  7. ICML 2026TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
  8. ICML 2026Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
  9. ICML 2026Understanding MARS: When Scaling Momentum Provably Helps
  10. ICML 2026Universal One-third Time Scaling in Learning Peaked Distributions
  11. ICML 2026Utility Boundary of Dataset Distillation: Scaling and Coverage Laws
  12. ICML 2026ViTok-v2: Scaling Native Resolution Autoencoders to 5 Billion Parameters
  13. ICML 2026WF-Bench: A Benchmark for Neural-Network WaveFunction Expressivity and Scaling Laws
  14. ICML 2026When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
  15. ICML 2026When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum Control
  16. ICML 2026Who Said Neural Networks Aren't Linear?
  17. NeurIPS 2026A Revisit of Hamiltonian Monte Carlo Efficiency on Bayesian Neural Networks
  18. NeurIPS 2026A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs
  19. NeurIPS 2026ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models
  20. NeurIPS 2026ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
  21. NeurIPS 2026Asymmetric Scaling Laws from Sparse Features
  22. NeurIPS 2026Bentkus-type asymptotic e-values
  23. NeurIPS 2026BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
  24. NeurIPS 2026CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
  25. NeurIPS 2026Compute-optimal data scaling for neural surrogates via multi-fidelity training
  26. NeurIPS 2026Conservation Laws for Diffusion Models
  27. NeurIPS 2026Consilience for Verifier-Free Test-Time Scaling
  28. NeurIPS 2026Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
  29. NeurIPS 2026Decomposing and Reshaping Scaling Laws through Token Learning Times
  30. NeurIPS 2026Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
  31. NeurIPS 2026Distributionally Robust Mixture-of-Experts Training
  32. NeurIPS 2026DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
  33. NeurIPS 2026Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling
  34. NeurIPS 2026Efficient Decoder Scaling Strategy for Constructive Neural Routing Solvers
  35. NeurIPS 2026Efficient Scaling of LLM Training with Flexible Context Parallelism
  36. NeurIPS 2026Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows
  37. NeurIPS 2026ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
  38. NeurIPS 2026Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
  39. NeurIPS 2026How Can SignSGD Outperform SGD? A Functional Scaling Law Perspective
  40. NeurIPS 2026How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
  41. NeurIPS 2026Hyperbolic Language Models: From Zipf to Compute-Optimal Scaling
  42. NeurIPS 2026It Just Takes Two: Scaling Amortized Inference to Large Sets
  43. NeurIPS 2026Language Denoising Objectives Extend the Value of Limited Data
  44. NeurIPS 2026Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
  45. NeurIPS 2026Meta-memorization and memorization scaling laws in transformers
  46. NeurIPS 2026MobileMoE: Scaling On-Device Mixture of Experts
  47. NeurIPS 2026Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
  48. NeurIPS 2026Neural Neural Scaling Laws
  49. NeurIPS 2026Neuron Populations Exhibit Divergent Selectivity with Scale
  50. NeurIPS 2026Norm Anchors Make Model Edits Last

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