Image de couverture de livre

OTARo: Once Tuning for All Precisions toward Robust On-Device LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Shaoyuan, Chen, Zhixuan, Yang, Dawei, Yuan, Zhihang, Wu, Qiang
Format:	Preprint
Publié:	2025
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

GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
par: Zhou, Sifan, et autres
Publié: (2025)

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
par: Hu, Xing, et autres
Publié: (2025)

RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
par: Xu, Chen, et autres
Publié: (2025)

SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training
par: Tareen, Shaharyar Ahmed Khan, et autres
Publié: (2025)

MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
par: Zhao, Zhixiong, et autres
Publié: (2026)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
par: Xu, Zukang, et autres
Publié: (2025)

Mixed-Precision Conjugate Gradient Solvers with RL-Driven Precision Tuning
par: Chen, Xinye
Publié: (2025)

PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling
par: Yue, Yuxuan, et autres
Publié: (2025)

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
par: Xu, Zukang, et autres
Publié: (2026)

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
par: Xiong, Zheyang, et autres
Publié: (2024)

CogFormer: Learn All Your Models Once
par: Huang, Jerry M., et autres
Publié: (2026)

Make Optimization Once and for All with Fine-grained Guidance
par: Shi, Mingjia, et autres
Publié: (2025)

Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization
par: Li, Zexi, et autres
Publié: (2024)

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
par: Hu, Xing, et autres
Publié: (2024)

Goal-Conditioned Agents that Learn Everything All at Once
par: Matthews, Michael, et autres
Publié: (2026)

Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML
par: Shaalan, Yassien
Publié: (2026)

OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
par: Hu, Xing, et autres
Publié: (2025)

Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
par: Zhang, Lijun, et autres
Publié: (2023)

Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers
par: Norgren, Victor
Publié: (2026)

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
par: Fan, Tao, et autres
Publié: (2026)

Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices
par: Song, Congzheng, et autres
Publié: (2025)

BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting
par: Li, Zhixuan, et autres
Publié: (2025)

PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs
par: Peng, Dan, et autres
Publié: (2024)

Memory-Optimized Once-For-All Network
par: Girard, Maxime, et autres
Publié: (2024)

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
par: Méloux, Maxime, et autres
Publié: (2025)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
par: Li, Ang, et autres
Publié: (2025)

BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations
par: Monninger, Thomas, et autres
Publié: (2026)

Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching
par: Karpukhin, Ivan, et autres
Publié: (2024)

GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices
par: Tu, Xiaolong, et autres
Publié: (2025)

From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices
par: Slamanig, Georg, et autres
Publié: (2025)

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
par: Wang, Jingyao, et autres
Publié: (2025)

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

Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs
par: Lee, Jung Hyun, et autres
Publié: (2025)

Emergent Response Planning in LLMs
par: Dong, Zhichen, et autres
Publié: (2025)

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
par: Yuan, Zhihang, et autres
Publié: (2026)

MobiLLM: Enabling LLM Fine-Tuning on the Mobile Device via Server Assisted Side Tuning
par: Li, Liang, et autres
Publié: (2025)

DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
par: Annavajjala, Aditya, et autres
Publié: (2024)

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
par: Fang, Wenzhi, et autres
Publié: (2025)

Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
par: Finkelshtein, Ben, et autres
Publié: (2025)

Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
par: Piening, Moritz, et autres
Publié: (2026)