The paper proposes SISA (SSM-Informed Softmax Attention), a novel hybrid attention mechanism that integrates state-space model (SSM) importance signals directly into the attention score, achieving sta…

Zamba2-VL is a new suite of vision-language models built on the Zamba2 hybrid architecture, achieving state-of-the-art performance and significantly improved inference efficiency compared to leading T…

This paper provides the first systematic threat analysis of State-Space Models (SSMs) in safety-critical applications, introducing novel attack classes and formal metrics to quantify their security an…

This paper introduces Bifocal dLLMs (R2LM), a new paradigm for discrete diffusion language models that combines causal and bidirectional attention for improved throughput and generation quality.

This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art perfor…

AEGIS introduces a novel physics-based system that analyzes encrypted network traffic flow dynamics, achieving state-of-the-art zero-day evasion detection with high accuracy and low latency.

CaMBRAIN introduces a novel Mamba-based State Space Model (SSM) for real-time, continuous EEG inference, achieving state-of-the-art results with significantly higher throughput than existing methods.