Cover Image

Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Da, Xue, Peng, Li, Yu, Liu, Yongxiang, Xu, Pengxiang, Zhang, Shixun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework
by: Zhang, Qingyue, et al.
Published: (2026)

Eigenpruning: an Interpretability-Inspired PEFT Method
by: Vergara-Browne, Tomás, et al.
Published: (2024)

PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs
by: Yu, Tongzhou, et al.
Published: (2025)

Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing
by: Cheng, Hailing, et al.
Published: (2026)

PEFT-MuTS: A Multivariate Parameter-Efficient Fine-Tuning Framework for Remaining Useful Life Prediction based on Cross-domain Time Series Representation Model
by: Fu, En, et al.
Published: (2026)

Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition
by: Mai, Zheda, et al.
Published: (2024)

Toward Conditional Distribution Calibration in Survival Prediction
by: Qi, Shi-ang, et al.
Published: (2024)

Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation
by: Naderi, Habibeh, et al.
Published: (2026)

GEM-Style Constraints for PEFT with Dual Gradient Projection in LoRA
by: Tekmen, Brian, et al.
Published: (2026)

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
by: Khetarpal, Khimya, et al.
Published: (2024)

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
by: Li, Pengxiang, et al.
Published: (2024)

A Unified Contrastive-Generative Framework for Time Series Classification
by: Liu, Ziyu, et al.
Published: (2025)

A Benchmark Study on Calibration
by: Tao, Linwei, et al.
Published: (2023)

Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Need
by: Wistuba, Martin, et al.
Published: (2024)

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
by: Luo, Yu, et al.
Published: (2024)

UniSymNet: A Unified Symbolic Network Guided by Transformer
by: Li, Xinxin, et al.
Published: (2025)

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
by: Flynn, Noah
Published: (2026)

UGMAE: A Unified Framework for Graph Masked Autoencoders
by: Tian, Yijun, et al.
Published: (2024)

UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
by: Zhang, Danhui, et al.
Published: (2026)

EEGAgent: A Unified Framework for Automated EEG Analysis Using Large Language Models
by: Zhao, Sha, et al.
Published: (2025)

Calibration and Transformation-Free Weight-Only LLMs Quantization via Dynamic Grouping
by: Zheng, Xinzhe, et al.
Published: (2025)

Confidence Calibration under Ambiguous Ground Truth
by: Tao, Linwei, et al.
Published: (2026)

Adjusting Regression Models for Conditional Uncertainty Calibration
by: Gao, Ruijiang, et al.
Published: (2024)

Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
by: Wei, Chu-Yuan, et al.
Published: (2025)

GRIT -- Geometry-Aware PEFT with K-FACPreconditioning, Fisher-Guided Reprojection, andDynamic Rank Adaptation
by: Saha, Pritish, et al.
Published: (2026)

UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
by: Li, Haosen, et al.
Published: (2026)

COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism
by: He, Jianing, et al.
Published: (2024)

Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
by: Wang, Xinjue, et al.
Published: (2026)

Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection
by: Yu, Manjiang, et al.
Published: (2025)

A Unified Invariant Learning Framework for Graph Classification
by: Sui, Yongduo, et al.
Published: (2025)

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
by: Zhou, Han, et al.
Published: (2023)

TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data
by: Suh, Namjoon, et al.
Published: (2024)

WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
by: Li, Xiaoyang, et al.
Published: (2025)

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving
by: Zhang, Yuchen, et al.
Published: (2025)

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
by: Li, Albus Yizhuo, et al.
Published: (2026)

TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage Prediction
by: Yu, Dahai, et al.
Published: (2026)

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
by: Yadav, Prateek, et al.
Published: (2023)

Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations
by: Xue, Kaiwen, et al.
Published: (2024)

A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees
by: Zhang, Miao, et al.
Published: (2025)

A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
by: Guo, Siyuan, et al.
Published: (2023)