Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models

• URL: http://arxiv.org/abs/2607.18280v1
• Date: Mon, 29 Jun 2026 01:33:30 GMT
• Title: Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
• Abstract summary: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation.<n>We study a minimalist compound sparsity framework that first applies low-rank approximation and channel pruning to obtain a statically compressed backbone.
• Score: 6.94102129809152
• License: http://creativecommons.org/licenses/by/4.0/
• 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. This work asks \emph{whether combining these two mechanisms can delay such degradation by distributing the compression burden}. We study a minimalist compound sparsity framework that first applies low-rank approximation and channel pruning to obtain a statically compressed backbone, and then introduces lightweight routers for per-token dynamic layer skipping. This design enables independent control of parameter sparsity and token-level computation sparsity. Experiments across language understanding and modeling benchmarks show that compound sparsity consistently outperforms single-mechanism compression under the same total sparsity, delaying the decay point on understanding tasks and preserving stronger modeling performance. Further analysis reveals cross-dimensional interference between parameter pruning and token skipping, and shows that near-balanced allocation is most effective under a fixed sparsity budget. These results demonstrate that compound compression provides a practical way to improve LLM compression, while revealing a broader cross-dimensional sparsity boundary that ultimately limits further compression. Code will be available at https://github.com/EIT-NLP/LLM-Pruning.

Related papers

• MixCompress: Mixture of Experts for Variable Rate Learned Image Compression [6.773101031620122]
  MixCompress is a unified variable bit-rate (VBR) framework based on sparse structural specialization.<n>We introduce a Mixture-of-Depths (MoD) extension to dynamically scale model capacity.
  arXiv  Detail & Related papers  (2026-07-15T19:57:15Z)
• Efficient Learned Image Compression without Entropy Coding [62.01837001379442]
  We present Entropy-Coding Free Learned Image Compression (EF-LIC)<n>EF-LIC is a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency.<n>Experiments show EF-LIC achieves up to 67.86% reduction over MS-ILLM on Kodak with LPIPS.
  arXiv  Detail & Related papers  (2026-05-22T07:37:30Z)
• PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression [43.524231862354405]
  LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors.<n>We propose PACE, a new framework that reformulates ancestral context aggregation as a non-causal backbone and causality to a lightweight, stage-scalable predictor.<n>Experiments demonstrate that PACE sets a new state-of-the-art in compression efficiency, achieving notable BD-BR savings and reducing decoding latency by over 90% in autoregressive mode.
  arXiv  Detail & Related papers  (2026-05-02T08:36:11Z)
• Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio [19.375601589555327]
  We introduce Semi-Dynamic Context Compression framework.<n>Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density.<n>Our framework consistently outperforms static baselines.
  arXiv  Detail & Related papers  (2026-03-26T21:36:55Z)
• Towards Practical Lossless Neural Compression for LiDAR Point Clouds [84.36825469211375]
  extreme sparsity of high-precision geometric details hinders efficient context modeling.<n>Our framework comprises two lightweight modules.<n>Experiments demonstrate competitive compression performance at real-time speed.
  arXiv  Detail & Related papers  (2026-03-26T10:02:07Z)
• Arbitrary Ratio Feature Compression via Next Token Prediction [52.10426317889982]
  Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
  arXiv  Detail & Related papers  (2026-02-12T02:38:57Z)
• HPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression [14.759497852655047]
  We propose HPC, a novel streaming dynamic Gaussian Splatting compression framework.<n>It employs a hierarchical point-based latent representation that operates on a per-Gaussian basis to avoid parameter redundancy in unoccupied space.<n>It achieves a storage reduction of 67% against its baseline while maintaining high reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-01-31T11:35:02Z)
• Compressing Many-Shots in In-Context Learning [61.231471139896506]
  We study an approach to improve the memory and computational efficiency of ICL inference by compressing the many-shot prompts.<n>We first show that existing prompt compression methods are ineffective for many-shot compression.<n>We propose MemCom, a layer-wise compression method.
  arXiv  Detail & Related papers  (2025-10-17T16:57:42Z)
• Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation [10.376875638696504]
  This work presents Any Compression via Iterative Pruning (ACIP), a novel algorithmic approach to determine a compression-performance trade-off.<n>We use an SVD-reparametrization of linear layers and iteratively prune their singular values with a sparsity-inducing penalty.<n>We show that ACIP seamlessly complements common quantization-based compression techniques.
  arXiv  Detail & Related papers  (2025-02-03T18:40:58Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective [85.08718140718707]
  UNComp is an uncertainty-aware framework that uncovers sparsity patterns that can be used for adaptive compression.<n>By focusing on uncertainty to analyze the sparsity pattern in detail, UNComp reduces the KV cache size to 4.74% of the original, achieves a 6% prefill speedup, and improves throughput by 6.4x.
  arXiv  Detail & Related papers  (2024-10-04T02:32:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.