Image de couverture de livre

LASER: Low-Rank Activation SVD for Efficient Recursion

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Çakar, Ege, Raghu, Ketan Ali, Zheng, Lia
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

Low-Rank Prehab: Preparing Neural Networks for SVD Compression
par: Qin, Haoran, et autres
Publié: (2025)

The Argument is the Explanation: Structured Argumentation for Trust in Agents
par: Cakar, Ege, et autres
Publié: (2025)

IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression
par: Abbasi, Ali, et autres
Publié: (2026)

Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression
par: Abbasi, Ali, et autres
Publié: (2026)

FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
par: Shao, Zishan, et autres
Publié: (2025)

Operator SVD with Neural Networks via Nested Low-Rank Approximation
par: Ryu, J. Jon, et autres
Publié: (2024)

Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces
par: Tong, William L., et autres
Publié: (2026)

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models
par: Wang, Haiyu, et autres
Publié: (2026)

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

Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
par: Solgi, Ryan, et autres
Publié: (2025)

DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
par: Ding, Xuan, et autres
Publié: (2025)

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast
par: Wu, Wenhao, et autres
Publié: (2026)

CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation
par: Liu, Ziyue, et autres
Publié: (2025)

Efficient Federated Low Rank Matrix Completion
par: Abbasi, Ahmed Ali, et autres
Publié: (2024)

Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression
par: Zhu, Hengyi, et autres
Publié: (2026)

Memory-Efficient Fine-Tuning via Low-Rank Activation Compression
par: Shi, Jiang-Xin, et autres
Publié: (2025)

SVD-NO: Learning PDE Solution Operators with SVD Integral Kernels
par: Koren, Noam, et autres
Publié: (2025)

Probe-Free Low-Rank Activation Intervention
par: Jiang, Chonghe, et autres
Publié: (2025)

AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression
par: Sinha, Atul Kumar, et autres
Publié: (2026)

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives
par: Wang, Qinsi, et autres
Publié: (2025)

Efficient GPU implementation of randomized SVD and its applications
par: Struski, Łukasz, et autres
Publié: (2021)

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

LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
par: Apolinario, Marco Paul E., et autres
Publié: (2025)

Low-Rank Learning by Design: the Role of Network Architecture and Activation Linearity in Gradient Rank Collapse
par: Baker, Bradley T., et autres
Publié: (2024)

Learning Neural Networks with Sparse Activations
par: Awasthi, Pranjal, et autres
Publié: (2024)

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
par: Jang, Kyoungseok, et autres
Publié: (2024)

Geometric Flow Models over Neural Network Weights
par: Erdogan, Ege
Publié: (2025)

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
par: Xu, Alec S., et autres
Publié: (2026)

R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
par: Zhang, Zhenyu, et autres
Publié: (2025)

Efficient Pre-Training of LLMs through Truncated SVD Layers
par: Kamali, Kaivan, et autres
Publié: (2026)

Efficient Generalized Low-Rank Tensor Contextual Bandits
par: Yi, Qianxin, et autres
Publié: (2023)

Efficient Pareto Manifold Learning with Low-Rank Structure
par: Chen, Weiyu, et autres
Publié: (2024)

ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity
par: Li, Jiaxi, et autres
Publié: (2026)

SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
par: Hong, Chengjie, et autres
Publié: (2026)

PCA, SVD, and Centering of Data
par: Kim, Donggun, et autres
Publié: (2023)

Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems
par: Kang, Yue, et autres
Publié: (2024)

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
par: González-Martínez, David
Publié: (2025)

$k$-SVD with Gradient Descent
par: Jedra, Yassir, et autres
Publié: (2025)

ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
par: Zhang, Yilang, et autres
Publié: (2025)

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