缩放定律论文趋势 2023–2026

主要结论

• 缩放定律论文从 2023 年的 60 篇增长到 2026 年的 248 篇，三年间扩大到约 4.1 倍。
• NeurIPS 是发缩放定律论文最多的会议，2023–2026 年共 221 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是时间序列：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 24 篇。
• 在「优化与缩放」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的低秩适配是 3.0 倍，缩放定律是 4.1 倍。

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

• NeurIPS 2026A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs
• ICML 2026A Capacity-Based Rationale for Multi-Head Attention
• ICLR 2026$\mathbf{Li_2}$: A Framework on Dynamics of Feature Emergence and Delayed Generalization
• CVPR 2026A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling
• NeurIPS 2025Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
• ICML 2025A Simple Model of Inference Scaling Laws
• ICLR 2025(Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning
• CVPR 2025D^3: Scaling Up Deepfake Detection by Learning from Discrepancy
• NeurIPS 2024An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem
• ICML 2024A Dynamical Model of Neural Scaling Laws
• ICLR 2024Principled Architecture-aware Scaling of Hyperparameters
• CVPR 2024From Activation to Initialization: Scaling Insights for Optimizing Neural Fields
• NeurIPS 2023Abide by the law and follow the flow: conservation laws for gradient flows
• ICML 2023Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
• ICLR 2023Distributionally Robust Post-hoc Classifiers under Prior Shifts
• CVPR 2023LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs
• NeurIPS 2026ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models
• ICML 2026Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
• ICLR 2026A universal compression theory: Lottery ticket hypothesis and superpolynomial scaling laws
• CVPR 2026MatAnyone 2 Scaling Video Matting via a Learned Quality Evaluator

全部缩放定律论文

共 96 篇，第 1 / 2 页

1. CVPR 2024Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields
2. CVPR 2024An Empirical Study of Scaling Law for Scene Text Recognition
3. CVPR 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling
4. CVPR 2024From Activation to Initialization: Scaling Insights for Optimizing Neural Fields
5. CVPR 2024InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
6. CVPR 2024Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic
7. CVPR 2024Scaling Laws of Synthetic Images for Model Training ... for Now
8. CVPR 2024Scaling Up Dynamic Human-Scene Interaction Modeling
9. CVPR 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
10. CVPR 2024Scaling Up Video Summarization Pretraining with Large Language Models
11. ICLR 2024Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
12. ICLR 2024EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
13. ICLR 2024Generalization error of spectral algorithms
14. ICLR 2024Lagrangian Flow Networks for Conservation Laws
15. ICLR 2024Language Modeling Is Compression
16. ICLR 2024Mitigating Emergent Robustness Degradation while Scaling Graph Learning
17. ICLR 2024On the Limitations of Temperature Scaling for Distributions with Overlaps
18. ICLR 2024Principled Architecture-aware Scaling of Hyperparameters
19. ICLR 2024Scaling Convex Neural Networks with Burer-Monteiro Factorization
20. ICLR 2024Scaling Laws for Associative Memories
21. ICLR 2024Scaling Laws for Sparsely-Connected Foundation Models
22. ICLR 2024Scaling Laws of RoPE-based Extrapolation
23. ICLR 2024Scaling Supervised Local Learning with Augmented Auxiliary Networks
24. ICLR 2024The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
25. ICLR 2024When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
26. ICML 2024A Dynamical Model of Neural Scaling Laws
27. ICML 2024A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
28. ICML 2024A Tale of Tails: Model Collapse as a Change of Scaling Laws
29. ICML 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
30. ICML 2024Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
31. ICML 2024Data Engineering for Scaling Language Models to 128K Context
32. ICML 2024Differentiable Model Scaling using Differentiable Topk
33. ICML 2024Explorations of Self-Repair in Language Models
34. ICML 2024Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
35. ICML 2024Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws
36. ICML 2024IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
37. ICML 2024Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
38. ICML 2024Mechanistic Design and Scaling of Hybrid Architectures
39. ICML 2024Mixtures of Experts Unlock Parameter Scaling for Deep RL
40. ICML 2024Navigating Scaling Laws: Compute Optimality in Adaptive Model Training
41. ICML 2024Offline Actor-Critic Reinforcement Learning Scales to Large Models
42. ICML 2024On the Embedding Collapse when Scaling up Recommendation Models
43. ICML 2024Position: Will we run out of data? Limits of LLM scaling based on human-generated data
44. ICML 2024Provably Scalable Black-Box Variational Inference with Structured Variational Families
45. ICML 2024Random Scaling and Momentum for Non-smooth Non-convex Optimization
46. ICML 2024RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
47. ICML 2024Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training
48. ICML 2024Scaling Down Deep Learning with MNIST-1D
49. ICML 2024Scaling Exponents Across Parameterizations and Optimizers
50. ICML 2024Scaling Laws for Fine-Grained Mixture of Experts

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。