The paper introduces LASER, a loss‑aware low‑rank compression framework for vision‑language models. It derives a curvature‑weighted SVD objective from a second‑order loss approximation and uses Kronecker‑factored Fisher information to guide decomposition toward downstream performance. LASER also proposes a cross‑layer rank allocation strategy based on calibration gradients and extends compression to feed‑forward networks with a hybrid SVD‑quantization scheme, achieving over 2.3× decoding speedup while maintaining accuracy under low‑precision inference.
arXiv:2606. 00573v1 Announce Type: new Abstract: Vision-language models (VLMs) deliver strong multimodal reasoning capabilities, but their large computational cost and high parameter counts make deployment challenging on resource-constrained devices.
arXiv:2509. 25136v3 Announce Type: replace Abstract: Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on activations.
The paper introduces FACTS, a structured Fisher Approximation for compressing Vision Transformers (ViTs) using Fisher-weighted SVD, which enforces token‑local aggregation while preserving within‑token activation‑gradient dependence. It also presents Constrained Rank Search (CoRS) to optimize layer‑wise rank allocation under a fixed FLOP budget. Experiments on ViTs and hybrid architectures show that FACTS improves accuracy‑efficiency trade‑offs, outperforming the strongest SVD baseline by up to +5.8 percentage points on Swin‑B without requiring finetuning.
arXiv:2510. 05544v2 Announce Type: replace-cross Abstract: Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment.
arXiv:2610.03389v1 Announce Type: cross Abstract: Vision language models (VLMs) incur substantial inference cost because every visual token is processed by the attention and MLP projections of every...
The paper introduces the "Compression Trinity," a unified framework that jointly applies sparsity, quantization, and low‑rank approximations to compress large language models. It presents several methods—MKOR, SLoPe, OPTIMA, PATCH, and SLiM—that leverage these three pillars to accelerate training, reduce memory bandwidth, and recover accuracy, achieving significant speedups and accuracy gains over existing techniques. The results demonstrate that combining all three compression strategies is essential for efficient, scalable, high‑performance LLM deployment.
arXiv:2607. 03057v1 Announce Type: cross Abstract: The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques.
arXiv:2508.03351v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-la...
arXiv:2606. 07098v1 Announce Type: cross Abstract: We present SigmaScale, a method for learning auxiliary scaling matrices $S$ to aid truncated Singular Value Decomposition (SVD) based Large Language Model (LLM) compression.
arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates co...
Prohibitive computational and environmental costs impede the scalable deployment of Large Language Models (LLMs). Traditional compression techniques (sparsity, quantization, low-rank approximations) a...
arXiv:2606. 05484v1 Announce Type: new Abstract: Pipeline parallelism enables training of large language models that exceed single-device memory, yet inter-stage activation communication becomes the dominant bottleneck when trained on low-bandwidth networks.