# GHOST: Unmasking Phantom States in Mamba2 via Grouped Hidden-state Output-aware Selection & Truncation

arXiv: https://arxiv.org/abs/2602.11408 · HTML: https://mlsanity.com/paper/2602.11408/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Layer-Adaptive State Pruning for Deep State Space Models](https://mlsanity.com/paper/2411.02824/) (2024)
- [On Pruning State-Space LLMs](https://mlsanity.com/paper/2502.18886/) (2025)
- [Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations](https://mlsanity.com/paper/2502.15790/) (2025)
- [SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot](https://mlsanity.com/paper/2506.09613/) (2025)
- [emgr - The Empirical Gramian Framework](https://mlsanity.com/paper/1611.00675/) (2016)
- [GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings](https://mlsanity.com/paper/2509.10844/) (2025)

## Built on by (most cited first, 1 of 1)

- [An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals](https://mlsanity.com/paper/2607.11796/) (2026)

## Abstract (arXiv)

While Mamba2's expanded state dimension enhances temporal modeling, it incurs substantial inference overhead that saturates bandwidth during autoregressive generation. Standard pruning methods fail to address this bottleneck: unstructured sparsity leaves activations dense, magnitude-based selection ignores runtime dynamics, and gradient-based methods impose prohibitive costs. We introduce GHOST (Grouped Hidden-state Output-aware Selection and Truncation), a structured pruning framework that approximates control-theoretic balanced truncation using only forward-pass statistics. By jointly measuring controllability and observability, GHOST rivals the fidelity of gradient-based methods without requiring backpropagation. As a highlight, on models ranging from 130M to 2.7B parameters, our approach achieves a 50% state-dimension reduction with approximately 1 perplexity point increase on WikiText-2. Code is available at https://anonymous.4open.science/r/mamba2ghost-7BCB/.