MatryoshkaLoRA inserts a crafted diagonal matrix P into LoRA to learn accurate nested low-rank adapters that support dynamic rank selection with minimal performance drop.
hub Canonical reference
A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
Canonical reference. 100% of citing Pith papers cite this work as background.
22
Pith papers citing it
Background
100% of classified citations
abstract
As large language models (LLMs) have become increasingly compute and memory intensive, parameter-efficient fine-tuning (PEFT) methods are now a common strategy to fine-tune LLMs. A popular PEFT method is Low-Rank Adapters (LoRA), which adds trainable low-rank "adapters" to selected layers. Each adapter consists of a low-rank matrix product, multiplicatively scaled by a rank-dependent factor. This scaling factor, which divides adapters by a factor of the rank, results in slowed learning and stunted performance for LoRA with higher-rank adapters. Consequently, the use of LoRA in practice has generally been limited to very low ranks. In this work, we study the impact of the scaling factor on the learning process and prove that LoRA adapters should be divided by a factor of the square root of the rank. Modifying LoRA with the appropriate scaling factor, which we call the rank-stabilized LoRA (rsLoRA) method, easily provides for a fine-tuning compute/performance trade-off, where larger ranks can be used to trade off increased computational resources during training for better fine-tuning performance, with no change in inference computing cost.
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
HAC provides a parameter-efficient way to move CLIP into hyperbolic geometry, yielding consistent gains on zero-shot VQA benchmarks without any VQA training data overlap.
DifFoundMAD improves differential morphing attack detection by replacing traditional embeddings with those from vision foundation models and applying class-balanced lightweight fine-tuning, cutting high-security error rates from 6.16% to 2.17%.
Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of the two static methods on SQL, medical QA, and counterfactual tasks while an efficient variant outperforms prior adaptive LoRA by up to 20%.
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
Frozen random backbones with low-rank LoRA adapters recover 96-100% of fully trained performance on diverse architectures while training only 0.5-40% of parameters.
InCoM achieves 23-28% higher success rates in mobile manipulation tasks by inferring motion intent for adaptive perception and decoupling base-arm action generation.
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled problems.
MLorc compresses optimizer momentum with low-rank methods to enable memory-efficient full fine-tuning of LLMs, outperforming LoRA and GaLore while matching full-parameter performance at small ranks.
LoCO is a PEFT technique that constructs orthogonal transformations via low-rank skew-symmetric matrices and compositional rotation chains with a parallelizable approximation, validated on transformer adaptations.
LoRA-Over injects auxiliary parameters into low-rank adapters during training and decomposes them back into standard LoRA at inference, with static or dynamic scheduling to allocate extra capacity where needed, yielding better generalization than vanilla LoRA on GLUE, MT-Bench, GSM8K and HumanEval.
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
SplitFT adapts cut-layer selection and reduces LoRA rank per client in federated split learning to improve efficiency and performance when fine-tuning LLMs on heterogeneous devices and data.
Fine-tuning Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali data enables effective generation where zero-shot fails, with Qwen3-8B performing best overall and Llama-3.1-8B showing the largest gains.
Constraining fine-tuning updates with LoRA mitigates performance degradation when switching from Adam to Muon on pretrained models.
Qwen2.5-3B was continued-pretrained and then fine-tuned with rsLoRA r256 on Sardinian data to reach 28.5 BLEU into the language, outperforming full fine-tuning and other LoRA variants.
A system based on OmniVoice with multi-model ensemble distillation for fine-tuning shows consistent gains in intelligibility metrics while keeping speaker similarity for cross-lingual scientific speech.
Tight integration of acoustic models with LLMs for ASR is ablated against shallow fusion across label units, fine-tuning strategies, LLM sizes, and joint CTC decoding to mitigate hallucinations.
The paper claims a selective fine-tuning method that identifies and freezes core parameters to mitigate catastrophic forgetting in LLMs while improving domain adaptation, shown in experiments with GPT-J and LLaMA-3.
citing papers explorer
-
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
MatryoshkaLoRA inserts a crafted diagonal matrix P into LoRA to learn accurate nested low-rank adapters that support dynamic rank selection with minimal performance drop.
-
HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA
HAC provides a parameter-efficient way to move CLIP into hyperbolic geometry, yielding consistent gains on zero-shot VQA benchmarks without any VQA training data overlap.
-
DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection
DifFoundMAD improves differential morphing attack detection by replacing traditional embeddings with those from vision foundation models and applying class-balanced lightweight fine-tuning, cutting high-security error rates from 6.16% to 2.17%.
-
PreFT: Prefill-only finetuning for efficient inference
Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.
-
Not How Many, But Which: Parameter Placement in Low-Rank Adaptation
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
-
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of the two static methods on SQL, medical QA, and counterfactual tasks while an efficient variant outperforms prior adaptive LoRA by up to 20%.
-
TLoRA: Task-aware Low Rank Adaptation of Large Language Models
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
-
A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
Frozen random backbones with low-rank LoRA adapters recover 96-100% of fully trained performance on diverse architectures while training only 0.5-40% of parameters.
-
InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
InCoM achieves 23-28% higher success rates in mobile manipulation tasks by inferring motion intent for adaptive perception and decoupling base-arm action generation.
-
ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled problems.
-
MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation
MLorc compresses optimizer momentum with low-rank methods to enable memory-efficient full fine-tuning of LLMs, outperforming LoRA and GaLore while matching full-parameter performance at small ranks.
-
LoCO: Low-rank Compositional Rotation Fine-tuning
LoCO is a PEFT technique that constructs orthogonal transformations via low-rank skew-symmetric matrices and compositional rotation chains with a parallelizable approximation, validated on transformer adaptations.
-
Strategic Over-Parameterization for Generalizable Low-Rank Adaptation
LoRA-Over injects auxiliary parameters into low-rank adapters during training and decomposes them back into standard LoRA at inference, with static or dynamic scheduling to allocate extra capacity where needed, yielding better generalization than vanilla LoRA on GLUE, MT-Bench, GSM8K and HumanEval.
-
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
-
SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning
SplitFT adapts cut-layer selection and reduces LoRA rank per client in federated split learning to improve efficiency and performance when fine-tuning LLMs on heterogeneous devices and data.
-
Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali
Fine-tuning Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali data enables effective generation where zero-shot fails, with Qwen3-8B performing best overall and Llama-3.1-8B showing the largest gains.
-
Can Muon Fine-tune Adam-Pretrained Models?
Constraining fine-tuning updates with LoRA mitigates performance degradation when switching from Adam to Muon on pretrained models.
-
LLiMba: Sardinian on a Single GPU -- Adapting a 3B Language Model to a Vanishing Romance Language
Qwen2.5-3B was continued-pretrained and then fine-tuned with rsLoRA r256 on Sardinian data to reach 28.5 BLEU into the language, outperforming full fine-tuning and other LoRA variants.
-
One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech
A system based on OmniVoice with multi-model ensemble distillation for fine-tuning shows consistent gains in intelligibility metrics while keeping speaker similarity for cross-lingual scientific speech.
-
LLMs and Speech: Integration vs. Combination
Tight integration of acoustic models with LLMs for ASR is ablated against shallow fusion across label units, fine-tuning strategies, LLM sizes, and joint CTC decoding to mitigate hallucinations.
-
Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization
The paper claims a selective fine-tuning method that identifies and freezes core parameters to mitigate catastrophic forgetting in LLMs while improving domain adaptation, shown in experiments with GPT-J and LLaMA-3.
- When PCOS Meets Eating Disorders: An Explainable AI Approach to Detecting the Hidden Triple Burden