EQ-VMamba adds rotation-equivariant cross-scan and group Mamba blocks to enforce end-to-end rotation equivariance, yielding better rotation robustness, competitive accuracy, and roughly 50% fewer parameters than non-equivariant baselines across classification, segmentation, and super-resolution.
Mamba: Linear-time sequence modeling with selective state spaces
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 8roles
method 1polarities
use method 1representative citing papers
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.
GraphScan replaces geometric or coordinate-based scanning in Vision SSMs with learned local semantic graph routing, yielding SOTA results among such models on classification and segmentation tasks.
Injecting RTG into states outside the autoregressive sequence yields shorter, more efficient Decision Transformers that outperform the original on offline RL tasks.
HyLo upcycles Transformer LLMs into hybrids with MLA and Mamba2/Gated DeltaNet blocks via staged training and distillation, extending context to 2M tokens and outperforming prior upcycled hybrids on long-context benchmarks.
CommFuse eliminates tail latency in communication-computation overlap for distributed LLM training by decomposing collective operations into P2P communications and fusing them with fine-grained computation scheduling.
MambaBack is a hybrid Mamba-CNN model with Hilbert sampling and chunked inference that reports better performance than seven prior methods on five whole-slide image datasets.
citing papers explorer
-
Rotation Equivariant Mamba for Vision Tasks
EQ-VMamba adds rotation-equivariant cross-scan and group Mamba blocks to enforce end-to-end rotation equivariance, yielding better rotation robustness, competitive accuracy, and roughly 50% fewer parameters than non-equivariant baselines across classification, segmentation, and super-resolution.
-
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.
-
Can Graphs Help Vision SSMs See Better?
GraphScan replaces geometric or coordinate-based scanning in Vision SSMs with learned local semantic graph routing, yielding SOTA results among such models on classification and segmentation tasks.
-
Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
Injecting RTG into states outside the autoregressive sequence yields shorter, more efficient Decision Transformers that outperform the original on offline RL tasks.
-
Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
HyLo upcycles Transformer LLMs into hybrids with MLA and Mamba2/Gated DeltaNet blocks via staged training and distillation, extending context to 2M tokens and outperforming prior upcycled hybrids on long-context benchmarks.
-
CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion for Distributed LLM Training
CommFuse eliminates tail latency in communication-computation overlap for distributed LLM training by decomposing collective operations into P2P communications and fusing them with fine-grained computation scheduling.
-
MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis
MambaBack is a hybrid Mamba-CNN model with Hilbert sampling and chunked inference that reports better performance than seven prior methods on five whole-slide image datasets.
- RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies