Image de couverture de livre

One-for-All Model Initialization with Frequency-Domain Knowledge

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Jianlu, Feng, Fu, Xie, Yucheng, Lv, Jiaqi, Geng, Xin
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling
par: Shen, Jianlu, et autres
Publié: (2026)

Knowledge Diversion for Efficient Morphology Control and Policy Transfer
par: Feng, Fu, et autres
Publié: (2025)

WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models
par: Feng, Fu, et autres
Publié: (2024)

Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization
par: Feng, Fu, et autres
Publié: (2026)

FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models
par: Xie, Yucheng, et autres
Publié: (2024)

Self-Supervised Weight Templates for Scalable Vision Model Initialization
par: Xie, Yucheng, et autres
Publié: (2026)

DivControl: Knowledge Diversion for Controllable Image Generation
par: Xie, Yucheng, et autres
Publié: (2025)

Transferring Core Knowledge via Learngenes
par: Feng, Fu, et autres
Publié: (2024)

Harmonizing Generalization and Personalization in Ring-topology Decentralized Federated Learning
par: Guo, Shunxin, et autres
Publié: (2025)

One for All: Towards Training One Graph Model for All Classification Tasks
par: Liu, Hao, et autres
Publié: (2023)

TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
par: Zhang, Yucheng, et autres
Publié: (2025)

One Model for All: Multi-Objective Controllable Language Models
par: He, Qiang, et autres
Publié: (2026)

GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning
par: Guo, Shunxin, et autres
Publié: (2025)

ProteinEngine: Empower LLM with Domain Knowledge for Protein Engineering
par: Shen, Yiqing, et autres
Publié: (2024)

On approximating the $f$-divergence between two Ising models
par: Feng, Weiming, et autres
Publié: (2025)

One Masked Model is All You Need for Sensor Fault Detection, Isolation and Accommodation
par: Fu, Yiwei, et autres
Publié: (2024)

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
par: Huang, Yongqi, et autres
Publié: (2025)

Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting
par: Ma, Qinwei, et autres
Publié: (2026)

Towards One-for-All Anomaly Detection for Tabular Data
par: Li, Shiyuan, et autres
Publié: (2026)

SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs
par: Chen, Hanzhu, et autres
Publié: (2024)

High-Energy Concentration for Federated Learning in Frequency Domain
par: Shi, Haozhi, et autres
Publié: (2025)

FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection
par: Cui, Jin, et autres
Publié: (2025)

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
par: Yao, Yuan, et autres
Publié: (2026)

Not All Language Model Features Are One-Dimensionally Linear
par: Engels, Joshua, et autres
Publié: (2024)

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
par: Kong, Lecheng, et autres
Publié: (2024)

Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation
par: Yuan, Jin, et autres
Publié: (2022)

Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity
par: Zhou, Yucheng, et autres
Publié: (2026)

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
par: Li, Hanyu, et autres
Publié: (2025)

Modeling All Response Surfaces in One for Conditional Search Spaces
par: Li, Jiaxing, et autres
Publié: (2025)

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
par: He, Xilin, et autres
Publié: (2024)

TabPFN: One Model to Rule Them All?
par: Zhang, Qiong, et autres
Publié: (2025)

Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models
par: Xia, Shi-Yu, et autres
Publié: (2024)

All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining
par: Zhao, Haihong, et autres
Publié: (2024)

FTMixer: Frequency and Time Domain Representations Fusion for Time Series Modeling
par: Li, Zhengnan, et autres
Publié: (2024)

HRP: High-Rank Preheating for Superior LoRA Initialization
par: Chen, Yuzhu, et autres
Publié: (2025)

Multimodal Large Language Models for Multi-Subject In-Context Image Generation
par: Zhou, Yucheng, et autres
Publié: (2026)

One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
par: Pu, Yuan, et autres
Publié: (2025)

One for All and All for One: GNN-based Control-Flow Attestation for Embedded Devices
par: Chilese, Marco, et autres
Publié: (2024)

Fre-CW: Targeted Attack on Time Series Forecasting using Frequency Domain Loss
par: Feng, Naifu, et autres
Publié: (2025)

DSDE: Using Proportion Estimation to Improve Model Selection for Out-of-Distribution Detection
par: Geng, Jingyao, et autres
Publié: (2024)