On Pruning State-Space LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Recent work proposed state-space models as an efficient alternative to transformers.
Approach: They propose to prune state-space models (SSMs) to reduce computation costs by using unstructured pruning methods.
Outcome: The proposed pruning methods show that they can be pruned to reduce their computation costs.

Similar Papers

Token Pruning for Improving Graph-Generating State Space Model Performance (2026.eacl-srw)

Copied to clipboard

Challenge: State Space Models (SSMs) are efficient alternatives to Transformers for sequence modeling, but extending them to two-dimensional vision tasks remains challenging.
Approach: They propose a leaf-guided pruning strategy that accelerates GG-SSM inference . they selectively scales or bypasses secondary refinement computations associated with leaf nodes .
Outcome: The proposed pruning strategy accelerates GG-SSM inference without modifying graph topology . the proposed pruning method achieves throughput improvements with controlled accuracy degradation .
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models (2025.acl-short)

Copied to clipboard

Challenge: State Space Models (SSMs) have emerged as efficient alternatives to Transformers, but their application to SSMs remains unexplored.
Approach: They propose a state-based PEFT method that adjusts state directly instead of using external prompts.
Outcome: The proposed method is based on state-offset tuning, which directly affects state at every timestep.
CodeSSM: Towards State Space Models for Code Understanding (2025.emnlp-main)

Copied to clipboard

Challenge: Existing transformers have limitations, such as quadratic complexity and high inference costs.
Approach: They propose a state space model that is trained on code corpora to assess its effectiveness.
Outcome: The proposed model reduces memory usage by up to 64% compared to transformers at a context length of 2048.
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments (2025.emnlp-main)

Copied to clipboard

Challenge: State-space models struggle with quadratic computational complexity, limiting their use in long-context tasks and resource-constrained input data.
Approach: They propose a pruning framework specifically tailored for Mamba that reduces parameter counts by 70% with only a 3–9% drop in performance.
Outcome: The proposed pruning framework achieves up to 70% parameter reduction with only a 3–9% drop in performance.
DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture.
Approach: They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers.
Outcome: The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks.
Rethinking Token Reduction for State Space Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% .
Approach: They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging.
Outcome: The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements.
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization (2024.emnlp-main)

Copied to clipboard

Challenge: minimizing reconstruction error is not always ideal and can overfit calibration data.
Approach: They propose a method to prune large language models by divide and conquer . they propose minimizing reconstruction error by more than 90% by using calibration data .
Outcome: The proposed pruning approach generates high reconstruction errors . the proposed technique reduces reconstruction error by more than 90% .
Efficient Classification of Long Documents via State-Space Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing transformer-based models can only process long documents with limited computational resources due to their quadratic computation time and space.
Approach: They propose to use state-space models for long document classification tasks instead of using sparse or hierarchical structures to solve this problem.
Outcome: The proposed model performs comparable to self-attention models while being 36% more efficient.
Two-Stage Regularization-Based Structured Pruning for LLMs (2026.acl-long)

Copied to clipboard

Challenge: Structural pruning is a promising solution for large language models . prior structured pruning methods remove unimportant parameters based on certain metrics .
Approach: They propose a structural pruning method that iteratively learns the weights of transformer layers by adding their l1-norm to the loss function.
Outcome: The proposed pruning method outperforms strong layer-wise pruning methods without requiring retraining.
BlockPruner: Fine-grained Pruning for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have significant computational and memory costs associated with training and inference.
Approach: They propose a training-free structured pruning approach that targets redundancies in MHA and MLP blocks.
Outcome: The proposed pruning approach achieves more granular and effective pruning compared to state-of-the-art pruning methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations