Architectures

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…

This paper proposes AD-Mamba, a multi-stage knowledge distillation framework that improves the performance of state space models in audio classification tasks.

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

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.

A new deep learning method, Mamba Transformer, is proposed for accurate single-shot 3D reconstruction from a single high frequency fringe image.

The paper demonstrates that the location and nature of state encoding in sequence models are not fixed architectural traits but are highly dependent on the specific task, showing that the encoding pro…

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.

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…

MARS proposes an encoder-agnostic aggregation operator that explicitly models multi-scale temporal structure in sequential recommendation, achieving state-of-the-art performance across both sparse and…

The paper introduces a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

This paper introduces EVOTS, an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for multivariate time-series forecasting.

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 proposes an alternative backbone for respiratory sound classification using State Space Models and introduces spectral-aware layer regularization and Dual-Axis Patch-Mix contrastive learnin…

This paper improves transformer-based neural operators to generalize to larger domains without retraining.

This paper proposes DAPGNet, a dynamic adaptive physics-guided graph diffusion network for hyperspectral image classification, which achieves state-of-the-art performance on four datasets.

This paper compares the performance of recurrent decoders and selective state-space models (Mamba) in intracortical brain-to-text systems, and investigates the impact of output targets (phonetic vs. c…

This paper proposes a fully SNN-based implementation of the Transformer decoder block for natural language processing, reducing energy consumption by 87-93%.

A regression-based approach is presented for Arabic dialect geolocation using a hierarchical neural architecture and spherical geodesic loss, achieving a median localization error of 481.2 km.

The paper proposes an SE ViT-BiLSTM hybrid model for enhanced intrusion detection in IIoT and IoMT environments, achieving superior performance on real-world datasets, especially after data balancing.