singular value decomposition

Integrating Independent Layer-Wise Rank Selection with Low-Rank SVD Training for Model Compression: A Theory-Driven Approach IJCAI 2025 KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models ICLR 2025 KIND: Knowledge Integration and Diversion for Training Decomposable Models ICML 2025 Large Language Model Evaluation via Matrix Nuclear-Norm EMNLP 2025 Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain IJCAI 2025 Learning to Stabilize Unknown LTI Systems on a Single Trajectory under Stochastic Noise UAI 2025 LESA: Learnable LLM Layer Scaling-Up ACL 2025 Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables ICCV 2025 LinearVC: Linear Transformations of Self-Supervised Features Through the Lens of Voice Conversion Interspeech 2025 LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning ICLR 2025 Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment ICML 2025 MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning NAACL 2025 MoDeGPT: Modular Decomposition for Large Language Model Compression ICLR 2025 Model merging with SVD to tie the Knots ICLR 2025 MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition ICML 2025 NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models EMNLP 2025 Nonconvex Linear System Identification with Minimal State Representation L4DC 2025 One-for-More: Continual Diffusion Model for Anomaly Detection CVPR 2025 Operator Learning for Hyperbolic PDEs JMLR 2025 Optimizing Lifelong Fine-Tuning for Multiple Tasks via Dataless Distribution Replay COLING 2025 Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection ICML 2025 Post-processing for Fair Regression via Explainable SVD AISTATS 2025 QERA: an Analytical Framework for Quantization Error Reconstruction ICLR 2025 Robust SAM: On the Adversarial Robustness of Vision Foundation Models AAAI 2025 R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference ICLR 2025