ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning

arXiv:2610.19700 · cs.LG · Submitted 2026-10-14 · Read on arXiv

cs.LG

Submitted: 2026-10-14

Updated: 2026-10-14

Code: https://github.com/Fanyao-Li/ReGRA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes

Sources

• Program Synthesis with Large Language Models
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• LoRA+: Efficient Low Rank Adaptation of Large Models
• Towards a Unified View of Parameter-Efficient Transfer Learning
• LoRA: Low-Rank Adaptation of Large Language Models
• A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
• DoRA: Weight-Decomposed Low-Rank Adaptation
• FreeAct: Freeing Activations for LLM Quantization
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning
• Continual Learning with Low Rank Adaptation
• Qwen3 Technical Report
• AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
• LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks