Image de couverture de livre

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Haiyu, Wang, Yutong, Li, Leshu, Ren, Yihui, Zhang, Sai Qian
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

WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
par: Wang, Haiyu, et autres
Publié: (2026)

QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
par: Wang, Yutong, et autres
Publié: (2025)

LASER: Low-Rank Activation SVD for Efficient Recursion
par: Çakar, Ege, et autres
Publié: (2026)

DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving
par: Yu, Fengze, et autres
Publié: (2025)

Compressing Large Language Models using Low Rank and Low Precision Decomposition
par: Saha, Rajarshi, et autres
Publié: (2024)

EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition
par: Nasiri, Hamid, et autres
Publié: (2025)

Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models
par: Zhang, Longteng, et autres
Publié: (2026)

PLAN: Proactive Low-Rank Allocation for Continual Learning
par: Wang, Xiequn, et autres
Publié: (2025)

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
par: Zhang, Stephen, et autres
Publié: (2024)

LASER: Attention with Exponential Transformation
par: Duvvuri, Sai Surya, et autres
Publié: (2024)

CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression
par: Kautsar, Muchammad Daniyal, et autres
Publié: (2025)

SARA: Singular-Value Based Adaptive Low-Rank Adaption
par: Gu, Jihao, et autres
Publié: (2024)

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
par: Saxena, Utkarsh, et autres
Publié: (2024)

Importance-Guided Basis Selection for Low-Rank Decomposition of Large Language Models
par: Asante, Daniel Agyei, et autres
Publié: (2026)

ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression
par: Xv, Lin, et autres
Publié: (2025)

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
par: Wang, Xin, et autres
Publié: (2024)

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
par: Horvath, Samuel, et autres
Publié: (2023)

FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
par: Zaccone, Riccardo, et autres
Publié: (2026)

Offline Reinforcement Learning with Generative Trajectory Policies
par: Feng, Xinsong, et autres
Publié: (2025)

The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
par: Li, Shiwei, et autres
Publié: (2025)

On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning
par: Ahmad, Muhammad, et autres
Publié: (2026)

AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption
par: Zhou, Yajie, et autres
Publié: (2025)

MUXQ: Mixed-to-Uniform Precision MatriX Quantization via Low-Rank Outlier Decomposition
par: Lee, Seoungsub, et autres
Publié: (2026)

MAP: Revisiting Weight Decomposition for Low-Rank Adaptation
par: Si, Chongjie, et autres
Publié: (2025)

TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
par: Mu, Lin, et autres
Publié: (2026)

CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
par: Wang, Zhuxuanzi, et autres
Publié: (2025)

SEMU: Singular Value Decomposition for Efficient Machine Unlearning
par: Sendera, Marcin, et autres
Publié: (2025)

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
par: He, Zhengfu, et autres
Publié: (2025)

Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models
par: Ghiasvand, Sajjad, et autres
Publié: (2025)

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
par: Rahmati, Amir Hossein, et autres
Publié: (2025)

BAQ: Efficient Bit Allocation Quantization for Large Language Models
par: Zhang, Chao, et autres
Publié: (2025)

Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
par: Emadi, Seyed Morteza
Publié: (2026)

Adaptive Rank Allocation for Federated Parameter-Efficient Fine-Tuning of Language Models
par: Wu, Fei, et autres
Publié: (2025)

Singular Value Decomposition on Kronecker Adaptation for Large Language Model
par: Chong, Yee Hin, et autres
Publié: (2025)

Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition
par: Liu, Ruyue, et autres
Publié: (2024)

Compressed BC-LISTA via Low-Rank Convolutional Decomposition
par: Wang, Han, et autres
Publié: (2026)

FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection
par: He, Yutong, et autres
Publié: (2026)

Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems
par: Tkach, Yevgeny
Publié: (2026)

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
par: Li, Yang, et autres
Publié: (2024)

Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation
par: Li, Yuhang, et autres
Publié: (2026)