Related papers: mHC-SSM: Manifold-Constrained Hyper-Connections fo…
Attention and State-Space Models (SSMs) when combined in a hybrid network in sequence or in parallel provide complementary strengths. In a hybrid sequential pipeline they alternate between applying a transformer to the input and then…
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream video analysis tasks. In this paper, we propose a Masked…
Stacked intelligent metasurfaces (SIMs), composed of multiple layers of reconfigurable transmissive metasurfaces, are gaining prominence as a transformative technology for future wireless communication security. This paper investigates the…
Compared to traditional Artificial Neural Network (ANN), Spiking Neural Network (SNN) has garnered widespread academic interest for its intrinsic ability to transmit information in a more energy-efficient manner. However, despite previous…
Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…
Large language models (LLMs) have significantly advanced generative applications in natural language processing (NLP). Recent trends in model architectures revolve around efficient variants of transformers or state-space/gated-recurrent…
Guided wave-based structural health monitoring (SHM) remains a powerful strategy for identifying early-stage defects and safeguarding vital aerospace structures. Yet, its practical use is often hindered by the enormous, high-dimensional…
Hybrid architectures combining state-space models with attention have achieved strong efficiency-quality tradeoffs, yet existing approaches either apply attention uniformly or learn static sparse patterns. This misses a key opportunity:…
This work presents the Parallelized Hierarchical Connectome (PHC), a general architectural framework that upgrades temporal-only State-Space Models (SSMs) into spatiotemporal recurrent networks. Conventional SSMs achieve parallel-scan…
State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured…
Structured State Space Models (SSMs) have emerged as alternatives to transformers. While SSMs are often regarded as effective in capturing long-sequence dependencies, we rigorously demonstrate that they are inherently limited by strong…
Dominant pan-sharpening frameworks simply concatenate the MS stream and the PAN stream once at a specific level. This way of fusion neglects the multi-level spectral-spatial correlation between the two streams, which is vital to improving…
While Separate Source-Channel Coding (SSCC) retains the practical benefits of modular system design, its effectiveness in noisy text transmission is fundamentally constrained by the fragility of autoregressive source decoding. In low-SNR…
State space models (SSMs) have emerged as a powerful framework for modelling long-range dependencies in sequence data. Unlike traditional recurrent neural networks (RNNs) and convolutional neural networks (CNNs), SSMs offer a structured and…
Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…
Today's high-performance architectures are increasingly constrained by data movement latency and energy overhead, as the slowdown of single-core performance scaling coincides with the rise of highly data-intensive workloads. In-memory…
Recently, DeepSeek has invented the manifold-constrained hyper-connection (mHC) approach which has demonstrated significant improvements over the traditional residual connection in deep learning models \cite{xie2026mhc}. Nevertheless, this…
State Space Models (SSMs) have emerged as a compelling alternative to attention models for long-range vision tasks, offering input-dependent recurrence with linear complexity. However, most efficient SSM variants reduce computation cost by…
How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data? Existing techniques often attempt to transfer powerful machine translation (MT) capabilities to ST, but neglect the…
Neural network quantum states (NQS) excel at approximating ground states of quantum many-body systems, but approximating all states of a degenerate manifold is nevertheless computationally expensive. We propose a single-trunk multi-head…