arXiv:2606.21847v2 Announce Type: replace-cross
Abstract: Low-rank decomposition is a promising compression paradigm for large language models (LLMs), yet its effectiveness hinges on rank budget allo...
By Chao Han, Yongjie Du, Junjie Tan, Zihao Xuan
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.
By Zhuowen Liu, Longkun Hao, Shiyu Feng, Xiaowen Chang, Ruiqun Li, Changqun Li
SkipCat introduces a rank‑maximized low‑rank compression framework for large language models, combining intra‑layer shared low‑rank projections and block‑skipping techniques to reduce redundancy and computational overhead. By allowing higher retained ranks while maintaining the same compression rate, SkipCat achieves a 7% accuracy improvement on zero‑shot tasks compared to prior low‑rank methods, all without additional fine‑tuning.
By Yu-Chen Lu, Sheng-Feng Yu, Hui-Hsien Weng, Pei-Shuo Wang, Yu-Fang Hu, Liang Hung-Chun, Hung-Yueh Chiang, Kai-Chiang Wu
LowRankArena is a standardized evaluation platform for SVD‑based low‑rank compression of large language models, unifying task versions, compression budgets, comparison regimes, and inference measurements. It provides a reproducible pipeline with over 3 TiB of released compressed checkpoints, enabling consistent comparisons across methods. An audit of five representative SVD techniques using LowRankArena shows that prior reported gains are highly conditional, with performance leaders and tiers shifting across backbones and keep ratios, and that nominal low‑rank savings often yield limited end‑to‑end speedups.
By Zishan Shao, Lixun Zhang, Kangning Cui, Wenhao Wu, Jinhee Kim, Yixiao Wang, Ting Jiang, Hancheng Ye, Qinsi Wang, Fan Yang, Danyang Zhuo, Yiran Chen, Hai Li
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.
By Ernests Lavrinovics, Marco Letizia, Roy Janco, Shai Segal, Johannes Bjerva, Maurizio Pierini
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.
By Ryan Solgi, Parsa Madinei, Jiayi Tian, Rupak Swaminathan, Jing Liu, Nathan Susanj, Zheng Zhang
The paper introduces SoCo, a compression framework that optimizes the singular spectrum of large language models using a learnable diagonal matrix to assign importance scores to SVD components. By progressively refining these scores through a three‑stage training process, SoCo adaptively prunes components while amplifying the importance of remaining ones, achieving a balance between aggressive compression and performance preservation. Experiments on multiple LLMs and benchmarks show that SoCo outperforms state‑of‑the‑art compression methods.
By Dengjie Li, Tiancheng Shen, Yao Zhou, Bernard Ghanem, Yibo Yang, Ming-Hsuan Yang
The paper introduces Layer-wise Error Modeling Search (LEMS) and KFAC-SVD to improve low-rank SVD-based compression of large language models. LEMS addresses global rank allocation by using a layer-wise error surrogate and an ILP formulation, while KFAC-SVD enhances decomposition quality by employing token-wise statistics to avoid rank collapse. Experiments on Mistral, Qwen3, and Llama 3 show LEMS yields up to 4.8 pp zero‑shot accuracy gains and KFAC‑SVD achieves an average perplexity improvement of 15%.
By Moritz Thoma, Maximilian Groezinger, Maximilian Forstenh\"ausler, Emad Aghajanzadeh, Manoj Rohit Vemparala, Christos Anagnostopoulos, Pierpaolo Mori, Nael Fasfous, Alexander Frickenstein, Daniel Mueller-Gritschneder, Ulf Schlichtmann
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.
By Moritz Thoma, Maximilian Groezinger, Maximilian Forstenh\"ausler, Emad Aghajanzadeh, Ryan Pegoud, Manoj Rohit Vemparala, Pierpaolo Mori, Alexander Frickenstein, Daniel Mueller-Gritschneder, Ulf Schlichtmann
The paper introduces Low‑Rank Conditional Computation (LRCC), a method that adds token‑dependent computation to pretrained language models by training lightweight routers to select among nested low‑rank paths while keeping low‑rank factors frozen. LRCC is evaluated on Llama and Qwen models, showing improved predictive performance over static low‑rank compression, including a 7.6‑percentage‑point gain in downstream accuracy on Llama‑2‑7B. The study also demonstrates that LRCC enhances perplexity and downstream accuracy on Llama‑3.2‑1B at matched decoding latency and analyzes the routers’ path choices to assess token‑wise path usefulness.
By Thomas Vaitses Fontanari, Maximo Eduardo Rulli, Federico Alvetreti, Donatella Genovese, Simone Scardapane
arXiv:2601. 16991v3 Announce Type: replace-cross Abstract: Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments.
By Longteng Zhang, Sen Wu, Shuai Hou, Zhengyu Qing, Zhuo Zheng, Danning Ke, Qihong Lin, Qiang Wang, Shaohuai Shi, Xiaowen Chu
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.
By Junghun Oh, Sungyong Baik, Kyoung Mu Lee