Data Efficient Neural Scaling Law via Model Reusing

Peihao Wang, Rameswar Panda, Zhangyang Wang

2/12/2026

No official code found. Best implementation: VITA-Group/Data-Efficient-Scaling (14 stars, last commit 2024-01-04).

Semantic Scholar

Code Implementations(1)

VITA-Group/Data-Efficient-ScalingCommunity68%

[ICML 2023] "Data Efficient Neural Scaling Law via Model Reusing" by Peihao Wang, Rameswar Panda, Zhangyang Wang

140Shell, PythonJun 1, 20232 years ago

data-efficientlarge-language-modelsmodel-reusingscaling-laws

Similar Papers

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle

100% match1 repo312026

Active Treatment Effect Estimation via Limited Samples

Improving Neural Logic Machines via Failure Reflection

Adapting Large Language Models via Reading Comprehension

Fast Excess Risk Rates via Offset Rademacher Complexity

Learning Fair Graph Representations via Automated Data Augmentations

Cite this paper

@article{wang2026data,
  title  = {Data Efficient Neural Scaling Law via Model Reusing},
  author = {Peihao Wang and Rameswar Panda and Zhangyang Wang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:36a329ecbd38c84b9706ccce933f60533338a530},
  journal = {ICML 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/36a329ecbd38c84b9706ccce933f60533338a530.svg)](https://codeofpaper.com/paper/36a329ecbd38c84b9706ccce933f60533338a530)

Discussion