Copertina

A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shen, Jianlu, Feng, Fu, Xu, Jiaze, Xie, Yucheng, Lv, Jiaqi, Geng, Xin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

One-for-All Model Initialization with Frequency-Domain Knowledge
di: Shen, Jianlu, et al.
Pubblicazione: (2026)

Knowledge Diversion for Efficient Morphology Control and Policy Transfer
di: Feng, Fu, et al.
Pubblicazione: (2025)

WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models
di: Feng, Fu, et al.
Pubblicazione: (2024)

Transferring Core Knowledge via Learngenes
di: Feng, Fu, et al.
Pubblicazione: (2024)

Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization
di: Feng, Fu, et al.
Pubblicazione: (2026)

DivControl: Knowledge Diversion for Controllable Image Generation
di: Xie, Yucheng, et al.
Pubblicazione: (2025)

FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models
di: Xie, Yucheng, et al.
Pubblicazione: (2024)

Self-Supervised Weight Templates for Scalable Vision Model Initialization
di: Xie, Yucheng, et al.
Pubblicazione: (2026)

Harmonizing Generalization and Personalization in Ring-topology Decentralized Federated Learning
di: Guo, Shunxin, et al.
Pubblicazione: (2025)

TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
di: Zhang, Yucheng, et al.
Pubblicazione: (2025)

A Deep Learning Framework for Sequence Mining with Bidirectional LSTM and Multi-Scale Attention
di: Yang, Tao, et al.
Pubblicazione: (2025)

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment
di: Xu, Wenzhe, et al.
Pubblicazione: (2026)

A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws
di: Li, Qinglun, et al.
Pubblicazione: (2026)

Enhancing Accuracy in Generative Models via Knowledge Transfer
di: Tian, Xinyu, et al.
Pubblicazione: (2024)

GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning
di: Guo, Shunxin, et al.
Pubblicazione: (2025)

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training
di: Xu, Minghao, et al.
Pubblicazione: (2025)

Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning
di: Shi, Ruxue, et al.
Pubblicazione: (2025)

Efficient Cross-Architecture Knowledge Transfer for Large-Scale Online User Response Prediction
di: Wu, Yucheng, et al.
Pubblicazione: (2026)

OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
di: Lu, Hongliang, et al.
Pubblicazione: (2025)

On approximating the $f$-divergence between two Ising models
di: Feng, Weiming, et al.
Pubblicazione: (2025)

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

A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization
di: Xu, Wenyuan, et al.
Pubblicazione: (2025)

Continual-NExT: A Unified Comprehension And Generation Continual Learning Framework
di: Qiao, Jingyang, et al.
Pubblicazione: (2026)

Rethinking Language Model Scaling under Transferable Hypersphere Optimization
di: Ren, Liliang, et al.
Pubblicazione: (2026)

Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
di: Wang, Yucheng, et al.
Pubblicazione: (2025)

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation
di: Qiao, Qiao, et al.
Pubblicazione: (2024)

CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
di: Ma, Jingying, et al.
Pubblicazione: (2025)

FedSGM: A Unified Framework for Constraint Aware, Bidirectionally Compressed, Multi-Step Federated Optimization
di: Upadhyay, Antesh, et al.
Pubblicazione: (2026)

A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer
di: Lu, Hanxiao, et al.
Pubblicazione: (2024)

A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systems
di: Eghbalzadeh, Hamid, et al.
Pubblicazione: (2025)

Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge
di: Zheng, Li, et al.
Pubblicazione: (2025)

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
di: Yao, Yuan, et al.
Pubblicazione: (2026)

Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment
di: Sun, Shengyang, et al.
Pubblicazione: (2025)

Cross-Paradigm Knowledge Distillation: A Comprehensive Study of Bidirectional Transfer Between Random Forests and Deep Neural Networks for Big Data Applications
di: Moghadasi, Mahdi Naser
Pubblicazione: (2026)

UniTrans: A Unified Vertical Federated Knowledge Transfer Framework for Enhancing Cross-Hospital Collaboration
di: Huang, Chung-ju, et al.
Pubblicazione: (2025)

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
di: Ruan, Jiaoyang, et al.
Pubblicazione: (2026)

MIP Candy: A Modular PyTorch Framework for Medical Image Processing
di: Fu, Tianhao, et al.
Pubblicazione: (2026)

FACTS: A Factored State-Space Framework For World Modelling
di: Nanbo, Li, et al.
Pubblicazione: (2024)

CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Values
di: Tang, Kai, et al.
Pubblicazione: (2025)