Tag

#SVD & Low-Rank

43 posts tagged with this label. Back to all tags or the main feed.

2026

09-26 EN

Scalable Kronecker-Fisher Approximation: What Cross-Layer Curvature Can Tell Us About Compression
09-26 中

Scalable Kronecker-Fisher 阅读笔记：压缩一层之后，另一层还安全吗？
09-25 EN

FACTS and CoRS: Which Curvature Should Low-Rank Compression Preserve?
09-25 中

FACTS 与 CoRS 阅读笔记：低秩压缩究竟该保留哪一种曲率？
09-24 EN

Deep Delta Learning: Editing the Residual Stream, and Accounting for the Cost
09-24 中

Deep Delta Learning 阅读笔记：怎样改写残差流，以及这次改写要付出什么代价
09-18 EN

SVD-LLM V2: Allocating Rank, Preserving Activations, and Understanding Local Optimality
09-18 中

SVD-LLM V2 阅读笔记：秩怎样分，激活怎样保，局部最优意味着什么
08-28 EN

LowRankArena: What Happens When You Force SVD Compression Papers to Play by the Same Rules
08-28 中

LowRankArena 阅读笔记：把 SVD 压缩论文放到同一套规则下会发生什么
08-14 EN

Chasing a Moving Target: Calibration and Rank-Allocation Drift in Training-Free Low-Rank LLM Compression
08-14 中

追着一个不断移动的目标：训练无关低秩压缩中的校准漂移与秩分配漂移
08-07 EN

SALT: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving
08-07 中

SALT 阅读笔记：子空间对齐质心-残差训练如何让超低秩 LoRA 服务成为可能
07-31 EN

DynaCalKV: Rethinking Fixed Head Grouping in Low-Rank KV Cache Compression
07-31 中

DynaCalKV 阅读笔记：低秩 KV Cache 压缩里，固定分组到底有多不合理
07-24 EN

SVD-Surgeon: Bringing Optimal Brain Surgeon to the Singular-Value Basis
07-24 中

SVD-Surgeon：把「最优脑外科手术」搬进奇异值空间
07-17 EN

LACE-SVD: Why Uniform Rank Budgets and Local Reconstruction Are Not Enough for SVD Compression
07-17 中

LACE-SVD 阅读笔记：均匀秩预算和局部重建为什么不够用了
07-10 EN

FlashSVD v1.5: Why Low-Rank LLMs Don't Get Faster on Their Own
07-10 中

FlashSVD v1.5：为什么低秩大模型不会自动变快
07-03 EN

AIR: Activation- and Influence-Aware SVD Compression for LLMs — Technical Review
07-03 中

AIR 阅读笔记：激活与影响力双重感知的SVD低秩LLM压缩
06-26 EN

SigmaScale: Learning to Scale Weight Matrices for Better SVD-Based LLM Compression
06-26 中

SigmaScale 阅读笔记：通过学习缩放矩阵改进 SVD 大语言模型压缩
06-19 EN

LASER: How Throwing Away 99% of a Weight Matrix Can Make LLMs Smarter
06-19 中

LASER：丢掉 99% 的矩阵秩，LLM 推理准确率反而提高了 27%
06-12 EN

SliceGPT: Post-Training LLM Compression via Computational Invariance
06-12 中

SliceGPT 阅读笔记：用计算不变性删除 Transformer 的行与列
05-29 EN

IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression
05-29 中

IO-SVD：基于输入输出双侧白化的自适应秩LLM压缩方法
05-22 EN

DoRA: Weight-Decomposed Low-Rank Adaptation — Technical Review
05-22 中

DoRA：权重分解低秩自适应——用幅度与方向解耦提升 LoRA 学习能力 | 阅读笔记
05-15 EN

Zero Sum SVD: A Global, Loss-Aware Rank Budget for LLM Compression
05-15 中

Zero Sum SVD：用「损失零和」做全局奇异值预算分配的 LLM 压缩方法
05-08 EN

Swift-SVD: Activation-Aware Low-Rank Compression for LLM Weights and KV Cache
05-01 EN

Low-Rank Optimization Trajectories for LLM RLVR Acceleration: A Technical Review of NExt
04-10 EN

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression — Deep Technical Review
04-10 中

SVD-LLM：面向大语言模型压缩的“截断感知”奇异值分解方法 — 深度阅读笔记
03-27 EN

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection — In-Depth Technical Review
03-23 EN

MiRA: A Subgoal-driven Framework for Improving Long-Horizon LLM Agents — Technical Review
03-13 EN

LoRA: Fine-Tuning Giant Models with Pocket Change — The Low-Rank Revolution