WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models

• URL: http://arxiv.org/abs/2604.02570v1
• Date: Thu, 02 Apr 2026 22:49:57 GMT
• Title: WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
• Abstract summary: Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs)<n>We introduce a new computational pattern and apply SVD at a finer granularity, enabling real and measurable improvements in execution latency.<n>We introducetextitWeighted SVD (WSVD), which outperforms other approaches by achieving over $1.8times$ decoding speedup while preserving accuracy.
• Score: 12.679057463090148
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such as image captioning and visual question answering. Although multiple prior works have proposed efficient SVD variants to enable low-rank operations, we find that in practice it remains difficult to achieve substantial latency reduction during model execution. To address this limitation, we introduce a new computational pattern and apply SVD at a finer granularity, enabling real and measurable improvements in execution latency. Furthermore, recognizing that weight elements differ in their relative importance, we adaptively allocate relative importance to each element during SVD process to better preserve accuracy, then extend this framework with quantization applied to both weights and activations, resulting in a highly efficient VLM. Collectively, we introduce~\textit{Weighted SVD} (WSVD), which outperforms other approaches by achieving over $1.8\times$ decoding speedup while preserving accuracy. We open source our code at: \href{https://github.com/SAI-Lab-NYU/WSVD}{\texttt{https://github.com/SAI-Lab-NYU/WSVD}

Related papers

• SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models [66.92079232778707]
  We propose Stage-Aware Dynamic Weighting (SAW) as a lightweight, algorithm-agnostic dynamic weighting mechanism.<n>SAW reweights each dimension's reward or advantage contribution by its relative informativeness within the batch.<n> Experiments on tool-calling and text summarization tasks demonstrate that SAW consistently improves both training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-06-05T10:00:19Z)
• IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression [21.844141881475533]
  SVD-based post-training compression offers a hardware-agnostic way to reduce model size and improve inference efficiency.<n>Existing methods often rely on input-only whitening spaces, homogeneous rank allocation, or loss-agnostic allocations.<n>We propose Input-Output Whitened SVD (IO-SVD), a post-training compression method that forms a KL-aware double-sided whitening space for model weights.
  arXiv  Detail & Related papers  (2026-05-15T05:19:10Z)
• Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement [27.517125673741486]
  Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic control.<n>We propose SD-VLA, a framework that disentangles visual inputs into multi-level static and dynamic tokens.<n>We introduce a new benchmark that more effectively evaluates the long-horizon temporal dependency modeling ability of VLAs.
  arXiv  Detail & Related papers  (2026-02-03T20:17:47Z)
• QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models [13.850959421148273]
  Vision-Language Models (VLMs) are integral to tasks such as image captioning and visual question answering.<n>Their high computational cost, driven by large memory footprints and processing time, limits their scalability and real-time applicability.<n>We propose leveraging Singular-Value Decomposition (SVD) over the joint query (Q), key (K), and value (V) weight matrices to reduce KV cache size and computational overhead.
  arXiv  Detail & Related papers  (2025-10-18T01:31:14Z)
• SpecVLM: Fast Speculative Decoding in Vision-Language Models [14.243294546325714]
  Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs)<n>We study speculative decoding for vision-language models (VLMs)<n>We introduce SpecVLM, a practical system that delivers 1.5--2.3x end-to-end speedups over full autoregressive inference.
  arXiv  Detail & Related papers  (2025-09-15T11:53:56Z)
• AdaSVD: Adaptive Singular Value Decomposition for Large Language Models [75.1196637934987]
  Singular Value Decomposition (SVD) has emerged as a promising compression technique for large language models (LLMs)<n>Existing SVD-based methods often struggle to effectively mitigate the errors introduced by SVD truncation.<n>We propose AdaSVD, an adaptive SVD-based LLM compression approach.
  arXiv  Detail & Related papers  (2025-02-03T14:34:37Z)
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)
• Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks [118.49566068398642]
  Cross-modal encoders for vision-language (VL) tasks are often pretrained with carefully curated vision-language datasets. Unimodal encoders are pretrained with simpler annotations that are less cost-prohibitive, achieving scales of hundreds of millions to billions. We propose Multimodal Adaptive Distillation (MAD), which adaptively distills useful knowledge from pretrained encoders to cross-modal VL encoders.
  arXiv  Detail & Related papers  (2022-04-22T04:41:04Z)
• An Empirical Study of Training End-to-End Vision-and-Language Transformers [50.23532518166621]
  We present METER(textbfMultimodal textbfEnd-to-end textbfTransformtextbfER), through which we investigate how to design and pre-train a fully transformer-based VL model. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-ViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion (e.g., merged attention vs. co-
  arXiv  Detail & Related papers  (2021-11-03T17:55:36Z)
• Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification [53.50708351813565]
  We propose SVD training, the first method to explicitly achieve low-rank DNNs during training without applying SVD on every step. We empirically show that SVD training can significantly reduce the rank of DNN layers and achieve higher reduction on computation load under the same accuracy.
  arXiv  Detail & Related papers  (2020-04-20T02:40:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.