State-space models are vulnerable to three new attack types that corrupt state integrity, with experiments showing up to 156x output changes and 6x higher targeted corruption than random inputs.
Decimamba: Exploring the length extrapolation potential of mamba.arXiv preprint arXiv:2406.14528
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
TTT3R derives a closed-form learning rate from memory-observation alignment confidence to boost length generalization in RNN-based 3D reconstruction by 2x in global pose estimation.
This work systematically compares inter-layer and intra-layer hybridization strategies for combining self-attention and Mamba-style state space models, evaluating them on language modeling, downstream tasks, long-context performance, scaling, and efficiency to derive optimal design recipes.
citing papers explorer
-
Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks
State-space models are vulnerable to three new attack types that corrupt state integrity, with experiments showing up to 156x output changes and 6x higher targeted corruption than random inputs.