Sparsifying Mamba (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing attempts to integrate sparsification with Mamba fail to leverage Mamba's internal structure for fine-grained sparsifying.
Approach: They propose to use Mamba to integrate sparsification into Mamba and propose a flexible and effective mechanism for parameter scalability.
Outcome: The proposed framework can independently achieve parameter scalability and has stronger performance.

Similar Papers

Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models (2025.naacl-long)

Copied to clipboard

Challenge: Large pre-trained models have achieved outstanding results in sequence modeling . alternative architectures, such as Selective Structured State Space Models (SSMs), have been proposed to address these inefficiencies.
Approach: They propose to reduce the size and computational overhead of large pre-trained models by removing selected components at different granularities.
Outcome: The proposed models achieve a speedup of up to 1.4x during inference while maintaining accuracy.
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.
Q-Mamba: Towards more efficient Mamba models via post-training quantization (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies show that Mamba architectures have room for further optimization in linear projections and state caches.
Approach: They propose a decoupled scale quantization scheme to mitigate outliers in states and channels by applying separate quantization scales.
Outcome: The proposed method reduces memory consumption by 50% across various quantization settings, model sizes, and generation and zero-shot tasks.
ReMamba: Equip Mamba with Effective Long-Sequence Modeling (2025.findings-emnlp)

Copied to clipboard

Challenge: Mamba models demonstrate superior inference efficiency and competitive performance on short-context tasks, but their capacity to comprehend long contexts is limited compared to transformer-based models.
Approach: They propose a model which incorporates selective compression and adaptation techniques within a two-stage re-forward process, incurring minimal additional inference costs overhead.
Outcome: The proposed model improves on the LongBench and L-Eval benchmarks by 3.2 and 1.6 points and attains performance almost on par with same-size transformer models.
Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling (2024.emnlp-main)

Copied to clipboard

Challenge: a task-agnostic visual encoding yields minimal performance gains on grounding, but Transformers outperform Mamba at in-context multimodal retrieval.
Approach: They propose to replace Transformers in Visual Language Models with Mamba, a structured state space model that demonstrates promising performance in sequence modeling.
Outcome: The proposed model outperforms Transformers-based models in captioning, question answering, and reading comprehension.
LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models (2025.acl-long)

Copied to clipboard

Challenge: State space models lack interpretability tools for long-context sequence modeling.
Approach: They propose a token-level decomposition method for Mamba-1 and Mamba-2 that enables fine-grained interpretability.
Outcome: The proposed method is able to reveal Mamba’s token-to-token interaction patterns across multiple tasks including translation, copying, and retrieval-based generation.
Mamba Knockout for Unraveling Factual Information Flow (2025.acl-long)

Copied to clipboard

Challenge: Recent work has introduced Mamba-based SSM architectures that rival Transformer performance in various settings.
Approach: They propose to use attentional interpretability techniques originally developed for Transformers to trace how information is transmitted and localized across tokens and layers.
Outcome: The proposed model disentangles how distinct features enable token-to-token information exchange or enrich individual tokens, thus offering a unified lens to understand Mamba internal operations.
Mamba Drafters for Speculative Decoding (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing drafters that use external drafters suffer from slower drafting while self-speculation methods use drafters tailored to the target model but require re-training.
Approach: They propose a drafter based on a state space model, Mamba, as a solution that combines the best aspects of both approaches.
Outcome: The proposed drafters outperform existing drafters while using less memory and maintaining their cross-model adaptability.
Sparsifying Transformer Models with Trainable Representation Pooling (2022.acl-long)

Copied to clipboard

Challenge: Existing approaches to sparsify attention in the Transformer model are based on quadratic memory complexity and a lack of information for each word.
Approach: They propose a method to sparsify attention in a Transformer model by learning to select the most-informative token representations during the training process.
Outcome: The proposed model performs better than the current SOTA model while being 1.8 faster during training, 4.5 faster inference and 13 more efficient in the decoder.
Exploring the Limitations of Mamba in COPY and CoT Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Inference overhead of Transformers increases linearly with the sequence length, posing challenges for modeling long sequences.
Approach: They analyze Mamba's expressive ability to perform COPY operations and Chain of Thought reasoning tasks using a defined sequence length.
Outcome: The proposed model can perform COPY operations and Chain of Thought reasoning tasks with a constant size while reducing computational costs.

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