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.
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.
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.
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. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.
MoARa introduces a module-aware rank allocation strategy and a block-wise magnitude-direction decomposition to improve low-rank gradient projection for large language model pre‑training. By profiling Transformer modules and tailoring projection ranks, it reduces the number of steps and wall‑clock time needed to reach target perplexity. Experiments on Llama, Qwen, and DeepSeek models show up to 41.7% fewer steps and 37.1% less training time with minimal memory overhead.
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.
ITC-MoE introduces an Importance-guided Token-aware Compression framework for Mixture-of-Experts Diffusion Language Models. It combines Adaptive Tucker Compression, which uses activation and gradient importance to jointly factorize expert weights and allocate ranks, with Token-aware Compensation and Routing that applies low‑rank adjustments to hot tokens and limits expert candidates for cold tokens. The method achieves significant reductions in computation and storage while maintaining generation quality, exemplified by a 30% compression budget that preserves 96.33% accuracy on MultiArith and delivers up to a 7.22× speedup.
arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keepin...
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:2607. 09694v1 Announce Type: new Abstract: Attention Residuals replace the fixed residual sum with depthwise attention over previous sub-layer outputs in large language models (LLMs), but use each output as both a full-dimensional key and value.
Prohibitive computational and environmental costs impede the scalable deployment of Large Language Models (LLMs). Traditional compression techniques (sparsity, quantization, low-rank approximations) a...
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.