Related papers: Asymmetric Virtual Memory Paging for Hybrid Mamba-…

State-space models (SSMs) offer efficient sequence modeling but lag behind Transformers on benchmarks that require in-context retrieval. Prior work links this gap to a small set of attention heads, termed Gather-and-Aggregate (G&A), which…

Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory…

Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting…

Recently the state space models (SSMs) with efficient hardware-aware designs, i.e., the Mamba deep learning model, have shown great potential for long sequence modeling. Meanwhile building efficient and generic vision backbones purely upon…

State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their adversarial robustness remains critically unexplored. This paper studies the phenomenon whereby…

The emergence of Mamba as an alternative to attention-based architectures has led to the development of Mamba-based self-supervised learning (SSL) pre-trained models (PTMs) for speech and audio processing. Recent studies suggest that these…

Tiered memory architectures have gained significant traction in the database community in recent years. In these architectures, the on-chip DRAM of the host processor is typically referred to as local memory, and forms the primary tier.…

Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or are often…

The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and…

We present PolyKV, a system in which multiple concurrent inference agents share a single, asymmetrically compressed KV cache pool. Rather than allocating a separate KV cache per agent -- the standard paradigm -- PolyKV writes a compressed…

We present Akasha 2, a state-of-the-art multimodal architecture that integrates Hamiltonian State Space Duality (H-SSD) with Visual-Language Joint Embedding Predictive Architecture (VL-JEPA). The system leverages the Mamba-3 Selective State…

The rapid adoption of large language models (LLMs) has shifted a substantial portion of inference workloads into throughput-oriented offline regimes, where fully utilizing GPU compute requires large batch sizes. However, existing…

The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes feature extraction and fusion processes more challenging.…

Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection.…

Heterogeneous Memory Architecture (HMA) aims to optimize memory usage by leveraging a combination of memory types, such as high-bandwidth memory (HBM), commodity DRAM, and non-volatile memory (NVM), when utilized as main memory. To achieve…

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…

Recent Mamba-based image restoration methods have achieved promising results but remain limited by fixed scanning patterns and inefficient feature utilization. Conventional Mamba architectures rely on predetermined paths that cannot adapt…

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

A heterogeneous memory has a single address space with fast access to some addresses (a fast tier of DRAM) and slow access to other addresses (a capacity tier of CXL-attached memory or NVM). A tiered memory system aims to maximize the…

Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features…