Imagen de Portada

Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yi-Kai, Zhan, De-Chuan, Ye, Han-Jia
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Model Assembly Learning with Heterogeneous Layer Weight Merging
por: Zhang, Yi-Kai, et al.
Publicado: (2025)

Parrot: Multilingual Visual Instruction Tuning
por: Sun, Hai-Long, et al.
Publicado: (2024)

$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts
por: Zhang, Yi-Kai, et al.
Publicado: (2026)

TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering
por: Ji, An-Yang, et al.
Publicado: (2026)

$V_0$: A Generalist Value Model for Any Policy at State Zero
por: Zhang, Yi-Kai, et al.
Publicado: (2026)

Wings: Learning Multimodal LLMs without Text-only Forgetting
por: Zhang, Yi-Kai, et al.
Publicado: (2024)

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
por: Li, Ming, et al.
Publicado: (2024)

OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions
por: Zhang, Yi-Kai, et al.
Publicado: (2024)

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning
por: Wu, Yang, et al.
Publicado: (2024)

Dr.LLM: Dynamic Layer Routing in LLMs
por: Heakl, Ahmed, et al.
Publicado: (2025)

DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
por: Shin, Haebin, et al.
Publicado: (2025)

Instruction Tuning for Large Language Models: A Survey
por: Zhang, Shengyu, et al.
Publicado: (2023)

Contrastive Instruction Tuning
por: Yan, Tianyi Lorena, et al.
Publicado: (2024)

The Best Instruction-Tuning Data are Those That Fit
por: Zhang, Dylan, et al.
Publicado: (2025)

ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities
por: Karger, Ezra, et al.
Publicado: (2024)

LongForm: Effective Instruction Tuning with Reverse Instructions
por: Köksal, Abdullatif, et al.
Publicado: (2023)

Instruction Tuning with Human Curriculum
por: Lee, Bruce W., et al.
Publicado: (2023)

Generative Representational Instruction Tuning
por: Muennighoff, Niklas, et al.
Publicado: (2024)

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
por: Li, Guanlin, et al.
Publicado: (2025)

RouteLLM: Learning to Route LLMs with Preference Data
por: Ong, Isaac, et al.
Publicado: (2024)

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
por: Toshniwal, Shubham, et al.
Publicado: (2024)

MathScale: Scaling Instruction Tuning for Mathematical Reasoning
por: Tang, Zhengyang, et al.
Publicado: (2024)

Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
por: Dai, Qirun, et al.
Publicado: (2025)

On the Effect of Instruction Tuning Loss on Generalization
por: Chatterjee, Anwoy, et al.
Publicado: (2025)

LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
por: Yuan, Liangqi, et al.
Publicado: (2025)

Instruction Mining: Instruction Data Selection for Tuning Large Language Models
por: Cao, Yihan, et al.
Publicado: (2023)

Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs
por: Ren, Yanwei, et al.
Publicado: (2025)

SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
por: Xie, Zhen-Hao, et al.
Publicado: (2026)

Fine-Tuning is Subgraph Search: A New Lens on Learning Dynamics
por: Li, Yueyan, et al.
Publicado: (2025)

SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe
por: Xiao, Yuxin, et al.
Publicado: (2024)

Dynamic Latent Routing
por: Yu, Fangyuan, et al.
Publicado: (2026)

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
por: Xia, Yuchen, et al.
Publicado: (2024)

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data
por: Zhang, Jipeng, et al.
Publicado: (2024)

Parameter Efficient Instruction Tuning: An Empirical Study
por: He, Pengfei
Publicado: (2024)

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
por: Sun, Lin, et al.
Publicado: (2025)

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
por: Zheng, Mingyu, et al.
Publicado: (2025)

Token-Level LLM Collaboration via FusionRoute
por: Xiong, Nuoya, et al.
Publicado: (2026)

Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
por: Zou, Junyi
Publicado: (2026)

Learning Dynamics of LLM Finetuning
por: Ren, Yi, et al.
Publicado: (2024)

TARo: Token-level Adaptive Routing for LLM Test-time Alignment
por: Rai, Arushi, et al.
Publicado: (2026)