From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control

Chi Zhang, Lianhai Ren, Jingpu Cheng, Qianxiao Li
2/14/2026

No official code found. Best implementation: czhang024/ParallelControl (15 stars, MIT, last commit 2026-04-26).

Semantic Scholar

Code Implementations(1)

czhang024/ParallelControlCommunity68%
MIT

ICML-2025 (Spotlight) "From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control"

150Shell, PythonMay 28, 20255 months agoMIT

Similar Papers

FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization

93% match2026

Stay on Topic with Classifier-Free Guidance

93% match2026

Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer

92% match2026

Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment

91% match2026

Repaint123: Fast and High-Quality One Image to 3D Generation with Progressive Controllable Repainting

91% match1 repo2762026

Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers

91% match2026

Cite this paper

@article{zhang2026from,
  title  = {From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control},
  author = {Chi Zhang and Lianhai Ren and Jingpu Cheng and Qianxiao Li},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:32134523c83eab03e639903e3a62e3e974254dd2},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/32134523c83eab03e639903e3a62e3e974254dd2.svg)](https://codeofpaper.com/paper/32134523c83eab03e639903e3a62e3e974254dd2)

Discussion