No article text was recorded for this version.
low-rank weight factorization (low-rank matrix factorization)
Version 1 of 125 papers25 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Application and Compression of Deep Time Delay Neural Network for Embedded Statistical Parametric Speech Synthesis
- Blog: FastLRNR and Sparse Physics Informed Backpropagation
- Blog: Speeding up deep neural network based speech recognition systems
- Blog: A Neural Autoregressive Approach to Collaborative Filtering
- Blog: Pufferfish: Communication-efficient Models At No Extra Cost
- Blog: Compressing deep neural networks using a rank-constrained topology
- Blog: SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
- Blog: A Survey on Model Compression for Large Language Models
- Blog: Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition
- Blog: Compact Speaker Embedding: lrx-Vector
- Blog: Introduction to the Special Section on Large-Scale Optimization for Audio, Speech, and Language Processing
- Blog: Compression of End-to-End Models
- Blog: An Efficient General-Purpose Optical Accelerator for Neural Networks
- Blog: Resource Efficient Deep Reinforcement Learning for Acutely Constrained TinyML Devices
- Blog: Compressing Pre-trained Language Models by Matrix Decomposition
- Blog: ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning
- Blog: Restructuring of deep neural network acoustic models with singular value decomposition
- Blog: PELA: Learning Parameter-Efficient Models with Low-Rank Approximation
- Blog: Structured Multi-Hashing for Model Compression
- Blog: Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation
- Blog: EdgeFace: Efficient Face Recognition Model for Edge Devices
- Blog: RETHINKING COMPRESSION: REDUCED ORDER MODELLING OF LATENT FEATURES IN LARGE LANGUAGE MODELS
- Blog: Neural Networks Compression for Language Modeling
- Blog: On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression
- Blog: A Survey on Efficient Vision-Language Models
History & citation
Current · Permanent link
- This direction split from Kronecker Product Factorization for Parameter Efficient Networks (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_low_rank_weight_factorization_low_rank_m_9568ca40,
title = {low-rank weight factorization (low-rank matrix factorization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/low-rank-weight-factorization-low-rank-matrix-factorization/rdr_9568ca4064d44b6b914167c3b83f3efc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_low_rank_weight_factorization_low_rank_m_9568ca40_v1,
title = {low-rank weight factorization (low-rank matrix factorization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/low-rank-weight-factorization-low-rank-matrix-factorization/rdr_9568ca4064d44b6b914167c3b83f3efc/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}