conftrace_

singular value decomposition

222 papers

Explore in graph

Also known as

SVD

Co-occurring keywords

model compression (3302) low-rank approximation (323) matrix factorization (529) low-rank adaptation (560) matrix completion (356) representation learning (6206) dimensionality reduction (720) convex optimization (1321) parameter-efficient fine-tuning (736) word embedding (1764)

Papers

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs ACL 2025
Large Language Model Evaluation via Matrix Nuclear-Norm EMNLP 2025
A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation JMLR 2025
Task Singular Vectors: Reducing Task Interference in Model Merging CVPR 2025
SVD-GCL: A Noise-Augmented Hybrid Graph Contrastive Learning Framework for Recommendation COLING 2025
One-for-More: Continual Diffusion Model for Anomaly Detection CVPR 2025
Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning ACL 2025
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations CVPR 2025
Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models AAAI 2025
Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Components AAAI 2025
NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models EMNLP 2025
Integrating Independent Layer-Wise Rank Selection with Low-Rank SVD Training for Model Compression: A Theory-Driven Approach IJCAI 2025
Operator Learning for Hyperbolic PDEs JMLR 2025
SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning CVPR 2025
Robust SAM: On the Adversarial Robustness of Vision Foundation Models AAAI 2025
DisLoRA: Task-specific Low-Rank Adaptation via Orthogonal Basis from Singular Value Decomposition EMNLP 2025
GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression EMNLP 2025
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness AAAI 2025
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression NAACL 2025
Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables ICCV 2025
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning ICCV 2025
Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement AAAI 2025
Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training RSS 2025
Insightful Instance Features for 3D Instance Segmentation CVPR 2025
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning NAACL 2025