Related papers: Akasha 2: Hamiltonian State Space Duality and Visu…

When predicting the next token in a sequence, vanilla transformers compute attention over all previous tokens, resulting in quadratic scaling of compute with sequence length. State-space models compress the entire sequence of tokens into a…

Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…

In this paper, we introduce Flash-VL 2B, a novel approach to optimizing Vision-Language Models (VLMs) for real-time applications, targeting ultra-low latency and high throughput without sacrificing accuracy. Leveraging advanced…

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

Remote sensing change detection (CD) has made significant advancements with the adoption of Convolutional Neural Networks (CNNs) and Transformers. While CNNs offer powerful feature extraction, they are constrained by receptive field…

Joint-embedding self-supervised learning (SSL) commonly relies on transformations such as data augmentation and masking to learn visual representations, a task achieved by enforcing invariance or equivariance with respect to these…

Real-time understanding of continuous video streams is essential for intelligent agents operating in high-stakes environments, including autonomous vehicles, surveillance drones, and disaster response robots. Yet, most existing video…

This paper introduces a high-performance hybrid algorithm, called Hybrid Hypervolume Maximization Algorithm (H2MA), for multi-objective optimization that alternates between exploring the decision space and exploiting the already obtained…

State Space Models (SSMs) and Hidden Markov Models (HMMs) are foundational frameworks for modeling sequential data with latent variables and are widely used in signal processing, control theory, and machine learning. Despite their shared…

In the emerging landscape of edge computing, the stochastic and bursty nature of serverless workloads presents a critical challenge for autonomous resource orchestration. Traditional reactive controllers, such as the Kubernetes Horizontal…

Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing powertrains. Conventional data-driven methods, such as…

Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this information into compact tokens. However, two challenges persist: (1) Suboptimal…

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.…

Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs), common across engineering domains, provide a formalism…

Image hash algorithms generate compact binary representations that can be quickly matched by Hamming distance, thus become an efficient solution for large-scale image retrieval. This paper proposes RV-SSDH, a deep image hash algorithm that…

Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing…

Serving the Intelligent Transport System (ITS) and Vehicle-to-Everything (V2X) tasks, roadside perception has received increasing attention in recent years, as it can extend the perception range of connected vehicles and improve traffic…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across a wide range of multimodal tasks. However, fine-tuning these models for domain-specific applications remains a computationally intensive challenge. This…

Numerous CNN-Transformer hybrid models rely on high-complexity global attention mechanisms to capture long-range dependencies, which introduces non-linear computational complexity and leads to significant resource consumption. Although…

Multi-modal medical image synthesis involves nonlinear transformation of tissue signals between source and target modalities, where tissues exhibit contextual interactions across diverse spatial distances. As such, the utility of a network…