A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges

arXiv:2610.12728 · cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/huggingface/peft

Terminology

• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 3 episodes

Sources

• Fine-Tuning of Transformer models with Frames
• Weight Updates as Activation Shifts: A Principled Framework for Steering
• Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
• Git Re-Basin: Merging Models modulo Permutation Symmetries
• RandLoRA: Full-rank parameter-efficient fine-tuning of large models
• Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product
• Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices
• Scaling Sparse Fine-Tuning to Large Language Models
• On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
• Implicit Regularization in Deep Matrix Factorization
• SliceGPT: Compress Large Language Models by Deleting Rows and Columns
• QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
• Exploring Visual Prompts for Adapting Large-Scale Models
• SingLoRA: Low Rank Adaptation Using a Single Matrix
• LoTR: Low Tensor Rank Weight Adaptation
• Sparse High Rank Adapters
• Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
• ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
• DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation
• Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods

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