PulseAugur
EN
LIVE 20:29:32
ENTITY singular value decomposition

singular value decomposition

PulseAugur coverage of singular value decomposition — every cluster mentioning singular value decomposition across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
21
113 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
18
107 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

7 day(s) with sentiment data

RECENT · PAGE 1/6 · 116 TOTAL
  1. RESEARCH · CL_352277 ·

    SinkState optimizes hybrid LLM serving with low-rank state compression

    Researchers have developed SinkState, a novel method to optimize the serving of hybrid Large Language Models (LLMs) by efficiently managing recurrent states. This technique leverages the observation that these states of…

  2. TOOL · CL_352259 ·

    New neurosymbolic inference pipelines boost weighted model counting accuracy

    Researchers have developed new pipelines for neurosymbolic inference that improve the accuracy of weighted model counting (WMC) by strategically allocating approximation budgets. These pipelines, inspired by tensor netw…

  3. TOOL · CL_351933 ·

    New RBLA+ method improves federated fine-tuning efficiency for AI models

    Researchers have developed RBLA+, an enhanced method for federated fine-tuning that efficiently extracts LoRA adapters for heterogeneous clients. This approach addresses the challenge of clients using different LoRA ran…

  4. TOOL · CL_351459 ·

    DeltaForge consolidates autonomous driving models using mixture-of-experts

    Researchers have developed DeltaForge, a novel post-hoc mixture-of-experts vision-language-action (VLA) model designed for autonomous driving. This approach consolidates multiple independently fine-tuned domain-specific…

  5. TOOL · CL_338534 ·

    Robotics Collective Cognition Framework Detailed in New Math Paper

    This paper presents a comprehensive mathematical framework for collective cognition in robotics, focusing on multimodal and collective estimation. It builds upon the Generalized Singular Value Decomposition (GSVD) to an…

  6. TOOL · CL_347832 ·

    SVD-Prune framework drastically cuts visual tokens in AI models

    Researchers have developed SVD-Prune, a novel framework designed to address the computational bottleneck in Vision-Language Models (VLMs) and Vision-Language-Action (VLA) models. This training-free method utilizes Singu…

  7. TOOL · CL_327348 ·

    New framework CRLoMTL improves multi-task learning with low-rank matrices

    Researchers have developed CRLoMTL, a novel framework designed to improve multi-task learning (MTL) in computer vision by addressing negative transfer. This method utilizes low-rank matrices to resolve conflicts between…

  8. TOOL · CL_327321 ·

    New COMPOT framework offers efficient transformer model compression

    Researchers have developed COMPOT, a new training-free framework for compressing transformer models. This method utilizes a calibration dataset to estimate sparse weight factorization through orthogonal dictionaries, en…

  9. TOOL · CL_324472 ·

    New TWA Method Enhances Out-of-Distribution Detection in AI Models

    Researchers have developed a new method called Rank-1 Weight-Corrected Trainable Weight Averaging (TWA) to improve out-of-distribution (OOD) detection in AI models. This technique builds upon existing TWA methods by inc…

  10. COMMENTARY · CL_324002 ·

    Singular Value Decomposition for Image Compression Explained

    This article explains how Singular Value Decomposition (SVD) can be used to compress images by breaking them down into layers. It highlights that the initial layers of an image contain the most significant information, …

  11. TOOL · CL_327481 ·

    Study reveals methods to enhance daily item embedding compatibility for CTR prediction

    A new study on arXiv explores methods to improve the compatibility of daily item embeddings, which are crucial for predicting user behavior like click-through rates (CTR). The research compares Word2Vec with an adaptati…

  12. TOOL · CL_321745 ·

    New LEMS and KFAC-SVD techniques boost LLM compression accuracy

    Researchers have developed a new method called Layer-wise Error Modeling Search (LEMS) to improve the compression of large language models (LLMs) using singular value decomposition (SVD). LEMS addresses limitations in e…

  13. TOOL · CL_339382 ·

    New methods boost LLM compression via SVD with accuracy gains

    Researchers have developed two new methods, Layer-wise Error Modeling Search (LEMS) and KFAC-SVD, to improve the compression of large language models using singular value decomposition (SVD). LEMS enhances rank allocati…

  14. TOOL · CL_312800 ·

    New OPLoRA method prevents catastrophic forgetting in LLM fine-tuning

    Researchers have introduced Orthogonal Projection LoRA (OPLoRA), a novel method to address catastrophic forgetting in parameter-efficient fine-tuning of large language models. This technique uses double-sided orthogonal…

  15. TOOL · CL_303401 ·

    New method tracks directional provenance in open-weight AI models

    Researchers have developed a new method called Witness Overlap to determine the directional provenance of open-weight models. This technique addresses the challenge of auditing model families that undergo frequent fine-…

  16. TOOL · CL_287020 ·

    Deep learning framework optimizes tri-hybrid MIMO precoding for enhanced wireless efficiency

    Researchers have developed a novel deep learning framework called Tri-PNet to optimize multi-user MIMO precoding in wireless communication systems. This framework integrates electromagnetic (EM)-reconfigurable antennas …

  17. TOOL · CL_285616 ·

    Linguistic theory visualized: Word proximity demo uses PPMI and SVD

    This demo illustrates a linguistic theory by visualizing word relationships in a 3D space. It uses Positive Pointwise Mutual Information (PPMI) to quantify how often words appear together more than chance would predict.…

  18. TOOL · CL_284345 ·

    New method computes Nash equilibria for cyber-defense games

    Researchers have developed a new method called Dynamical Low-Rank Equilibrium Computation (DLR-NE) to efficiently compute Nash equilibria for stochastic games, particularly in the context of industrial control systems (…

  19. RESEARCH · CL_280405 ·

    New research reframes SVD as core ML algorithm, extends to multi-source learning

    Two new research papers explore the geometric underpinnings and applications of Singular Value Decomposition (SVD) in machine learning. The first paper re-examines SVD from a geometric perspective, demonstrating how its…

  20. TOOL · CL_277360 ·

    New symmetric autoencoders offer theoretical foundation for deep learning

    Researchers have introduced a new class of deep learning architectures called symmetric autoencoders, offering a more robust theoretical foundation compared to existing methods. This work formally distinguishes between …