Structured Sparsity

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 33

All topics

SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask
May 7, 2026Liu Hanzuo, Chaofan Lin, Weixuan Sun +4LLM Pruning Sparse Recovery
†Tsinghua University · ‡Tencent
Proximal Projection for Doubly Sparse Regularized Models
May 6, 2026Jia Wei He, R. Ayesha Ali, Gerarda DarlingtonStructured Sparsity Linear Regression
Department of Mathematics & Statistics , University of Guelph
PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
Sep 27, 2025Younes Hourri, Mohammad Mozaffari, Maryam Mehri DehnaviLLM Pruning LLM Compression
Department of Computer Science University of Toronto

May 7, 2026, cs.LGJ/K move · Enter open · S save

SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask

Liu Hanzuo, Chaofan Lin, Weixuan Sun, Yulong Wang+3

†Tsinghua University · ‡Tencent

LLM Pruning Sparse Recovery Structured Sparsity Neural Network Pruning

Open paper AskPDF arXiv

Semi-structured sparsity provides a practical path to accelerate large language models (LLMs) with native hardware support, but post-training semi-structured pruning often suffers from substantial quality degradation due to strong structural coupling. Existing methods rely on large-scale sparse retraining to recover accuracy, resulting in high computational cost. We propose SparseForge, a post-training framework that improves recovery efficiency by directly optimizing the sparsity mask rather than scaling up retraining tokens. SparseForge combines Hessian-aware importance estimation with progressive annealing of soft masks into hardware-executable structured sparsity, enabling stable and efficient sparse recovery. On LLaMA-2-7B under 2:4 sparsity, SparseForge achieves 57.27% average zero-shot accuracy with only

\textbf{5B}

retraining tokens, surpassing the dense model's 56.43% accuracy and approaching the 57.52% result of a state-of-the-art method using

\textbf{40B}

tokens. Such improvements on the accuracy-efficiency trade-off from SparseForge are shown to be consistent across model families.

Momentum

Related topics

Latest papers 33

SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask

Proximal Projection for Doubly Sparse Regularized Models

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs