Cover Image

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Tianyi, Lin, Pengxiao, Wang, Zhiwei, Xu, Zhi-Qin John
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
by: Zhang, Zhongwang, et al.
Published: (2024)

Identity Bridge: Enabling Implicit Reasoning via Shared Latent Memory
by: Lin, Pengxiao, et al.
Published: (2025)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
by: Zhang, Zhongwang, et al.
Published: (2025)

Reasoning Bias of Next Token Prediction Training
by: Lin, Pengxiao, et al.
Published: (2025)

Focus and Dilution: The Multi-stage Learning Process of Attention
by: Chen, Zheng-An, et al.
Published: (2026)

MetMamba: Regional Weather Forecasting with Spatial-Temporal Mamba Model
by: Qin, Haoyu, et al.
Published: (2024)

Mamba Modulation: On the Length Generalization of Mamba
by: Lu, Peng, et al.
Published: (2025)

The Achilles Heel of AI: Fundamentals of Risk-Aware Training Data for High-Consequence Models
by: Cook, Dave, et al.
Published: (2025)

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
by: Singh, Joykirat, et al.
Published: (2024)

PackMamba: Efficient Processing of Variable-Length Sequences in Mamba training
by: Xu, Haoran, et al.
Published: (2024)

SMILES-Mamba: Chemical Mamba Foundation Models for Drug ADMET Prediction
by: Xu, Bohao, et al.
Published: (2024)

Protein-Mamba: Biological Mamba Models for Protein Function Prediction
by: Xu, Bohao, et al.
Published: (2024)

Efficient and Flexible Method for Reducing Moderate-size Deep Neural Networks with Condensation
by: Chen, Tianyi, et al.
Published: (2024)

MambaNet: Mamba-assisted Channel Estimation Neural Network With Attention Mechanism
by: Luan, Dianxin, et al.
Published: (2026)

TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model
by: Li, Yixing, et al.
Published: (2025)

Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting
by: Liang, Aobo, et al.
Published: (2024)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
by: Xu, Zukang, et al.
Published: (2025)

Kinetic-Mamba: Mamba-Assisted Predictions of Stiff Chemical Kinetics
by: Pandey, Additi, et al.
Published: (2025)

MCST-Mamba: Multivariate Mamba-Based Model for Traffic Prediction
by: Hamad, Mohamed, et al.
Published: (2025)

eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing
by: Kim, Jiyong, et al.
Published: (2025)

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition
by: Yang, Chenhongyi, et al.
Published: (2024)

InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model
by: Wang, Youjin, et al.
Published: (2026)

DeciMamba: Exploring the Length Extrapolation Potential of Mamba
by: Ben-Kish, Assaf, et al.
Published: (2024)

A Survey of Mamba
by: Qu, Haohao, et al.
Published: (2024)

DYNAMAX: Dynamic computing for Transformers and Mamba based architectures
by: Nogales, Miguel, et al.
Published: (2025)

Mamba Hawkes Process
by: Gao, Anningzhe, et al.
Published: (2024)

Is Mamba Effective for Time Series Forecasting?
by: Wang, Zihan, et al.
Published: (2024)

DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone
by: Singh, Vaibhav, et al.
Published: (2025)

ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
by: Karadag, Yusuf Meric, et al.
Published: (2025)

MedMamba: Recasting Mamba for Medical Time Series Classification
by: He, ZhengXiao, et al.
Published: (2026)

Mamba Meets Financial Markets: A Graph-Mamba Approach for Stock Price Prediction
by: Mehrabian, Ali, et al.
Published: (2024)

MambaCapsule: Towards Transparent Cardiac Disease Diagnosis with Electrocardiography Using Mamba Capsule Network
by: Xu, Yinlong, et al.
Published: (2024)

NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba
by: Wang, Tongze, et al.
Published: (2024)

MambaOut: Do We Really Need Mamba for Vision?
by: Yu, Weihao, et al.
Published: (2024)

MambaSL: Exploring Single-Layer Mamba for Time Series Classification
by: Jung, Yoo-Min, et al.
Published: (2026)

BioMamba: Leveraging Spectro-Temporal Embedding in Bidirectional Mamba for Enhanced Biosignal Classification
by: Qian, Jian, et al.
Published: (2025)

Scalable Complexity Control Facilitates Reasoning Ability of LLMs
by: Hang, Liangkai, et al.
Published: (2025)

Is Mamba Capable of In-Context Learning?
by: Grazzi, Riccardo, et al.
Published: (2024)

Differential Mamba
by: Schneider, Nadav, et al.
Published: (2025)

Decision Mamba Architectures
by: Correia, André, et al.
Published: (2024)