用低秩残差压缩给分割学习“减负”，通信开销大减，隐私与效率兼得的新思路。
arXiv:2608.23018v1 Announce Type: cross Abstract: Federated fine-tuning of on-device large language models (LLMs) faces a significant computing burden…
深入剖析免训练低秩压缩中校准与截断误差的传播机制，为LLM高效压缩提供理论支撑。
arXiv:2608.08506v1 Announce Type: new Abstract: Training-free low-rank compression frameworks have been gaining prominence for LLM compression given t…
揭秘大脑连续工作记忆的数学机制，看归一化如何塑造低秩慢流形。
arXiv:2608.01947v1 Announce Type: cross Abstract: The ability to robustly maintain and update continuous variables is a hallmark of working memory. Wh…
低秩预训练大模型遭遇不稳定困境？这项ICML 2026研究提出原生低秩LLM预训练的稳定化方法，兼顾效率与质量。
arXiv:2602.12429v2 Announce Type: replace Abstract: Foundation models have achieved remarkable success, yet their growing parameter counts pose signif…
用张量列低秩分解攻克扩散模型高维采样难题，带来理论与计算效率双重飞跃。
arXiv:2607.06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learn…
提出统一秩分配方法，突破低秩分解压缩LLM的瓶颈，兼顾效率与性能。
arXiv:2606.21847v1 Announce Type: cross Abstract: Low-rank decomposition serves as a promising compression paradigm for large language models, however…
新型SVD压缩框架，利用反向信号影响度量引导低秩近似，在保持大模型功能的同时实现高效压缩。
arXiv:2606.19993v1 Announce Type: new Abstract: We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that gu…
边缘设备微调LLM的突破：LoRA峰值内存优化技术详解
arXiv:2606.19528v1 Announce Type: cross Abstract: Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data o…
从副作用的根源剖析LLM行为干预，低秩子空间分析精准定位，为安全控制提供新视角
arXiv:2606.14388v1 Announce Type: new Abstract: Interventions designed to modify a particular behavior in LLMs, such as refusal or sycophancy, often p…
提出基于低秩因子的LLM评估新范式，突破传统基准分数局限，揭示模型真实能力。
arXiv:2507.20208v2 Announce Type: replace Abstract: Current evaluations of large language models (LLMs) rely heavily on a growing collection of benchm…
将低秩最优传输问题转化为黎曼流形上的优化，显著提升计算效率与可扩展性，理论突破值得关注。
arXiv:2606.12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing app…
新方法Swift-SVD实现理论最优性与实际效率兼得，专为低秩大模型压缩而生，ICML 2026收录。
arXiv:2604.01609v2 Announce Type: replace Abstract: The deployment of Large Language Models is constrained by the memory and bandwidth demands of stat…
仅靠排序即可实现大模型张量化，比传统分解方法更简洁高效，是LLM压缩与加速的新范式
arXiv:2606.08565v1 Announce Type: new Abstract: Tensor networks provide efficient representations for compressing large neural networks. By carefully …
用SVD低秩分解加学习缩放矩阵，实现高效LLM压缩，精准降维保性能。
arXiv:2606.07098v1 Announce Type: cross Abstract: We present SigmaScale, a method for learning auxiliary scaling matrices $S$ to aid truncated Singula…
重新审视低秩适应（LoRA）在私有LLM微调中的应用，探讨差分隐私与效率的平衡。
arXiv:2510.01137v3 Announce Type: replace Abstract: Privacy is a central concern when fine-tuning large language models (LLMs) on sensitive data, and …
NaRA提出噪声感知LoRA，显著提升扩散大语言模型参数高效微调效果
arXiv:2605.29716v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative para…
截断SVD层如何让LLM预训练更高效？本文揭示低秩表示与正交约束的优化新思路。
arXiv:2605.28573v1 Announce Type: cross Abstract: The massive scaling of Large Language Models (LLMs) has made pretraining increasingly cost-prohibiti…
揭示RLVR训练中参数轨迹的秩一结构，仅需极小规模训练即可外推LLM推理能力，颠覆传统认知。
arXiv:2605.21468v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving rea…
蒸馏+低秩适配器让视频生成仅需一两个采样步，颠覆传统扩散流程性能
Distillation + low‑rank tricks cut compute Combining knowledge distillation with low‑rank adapters now yields video generators that need only one or t…
提出基于校准不确定度的LLM级联路由方案，在保持性能的同时降低推理成本。
arXiv:2605.18796v1 Announce Type: new Abstract: LLM cascades and model routing promise lower inference cost by sending easy queries to a small model a…