arXiv:2606. 19993v1 Announce Type: new Abstract: We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that guides each weight matrix's low-rank approximation with a backward-signal influence metric.
arXiv:2605.28573v2 Announce Type: replace-cross Abstract: LLM pretraining is extremely costly; therefore, parameter-efficient LLM architectures have recently emerged as a compelling research directio...
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: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:2602.02848v2 Announce Type: replace Abstract: Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD...
arXiv:2608. 08506v1 Announce Type: new Abstract: Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter count while maintaining task-level accuracy.
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:2605. 30836v2 Announce Type: replace Abstract: Recent SVD based compression methods for large language models like SVD LLM and Basis Sharing can be unified under one optimization problem.
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: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.
arXiv:2607. 11940v1 Announce Type: cross Abstract: As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging.
arXiv:2606. 16454v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pre-trained models to downstream tasks by parameterizing weight updates with low-rank matrices.
arXiv:2608.23018v1 Announce Type: cross Abstract: Federated fine-tuning of on-device large language models (LLMs) faces a significant computing burden. To overcome this limitation, split learning (SL...