Related papers: Adaptive and Robust Image Processing on CubeSats

In recent years, Deep Learning (DL) has found great success in domains such as multimedia understanding. However, the complex nature of multimedia data makes it difficult to develop DL-based software. The state-of-the art tools, such as…

In this paper, we describe DiOS, a lightweight model operating system which can be used to execute programs that make use of POSIX APIs. Such executions are fully reproducible: running the same program with the same inputs twice will result…

Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression and efficiency enhancement. However, existing methods often…

Operational hazards in Manufacturing Industrial Internet (MII) systems generate severe data outliers that cripple traditional statistical analysis. This paper proposes a novel robust regression method, DPD-Lasso, which integrates Density…

The study of complex many-body systems via analysis of the trajectories of the units that dynamically move and interact within them is a non-trivial task. The workflow for extracting meaningful information from the raw trajectory data is…

It is important to design compact language models for efficient deployment. We improve upon recent advances in both the language modeling domain and the model-compression domain to construct parameter and computation efficient language…

Pipeline parallelism is widely used to train large language models (LLMs). However, increasing heterogeneity in model architectures exacerbates pipeline bubbles, thereby reducing training efficiency. Existing approaches overlook the…

Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are…

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability…

Fast-evolving artificial intelligence (AI) algorithms such as large language models have been driving the ever-increasing computing demands in today's data centers. Heterogeneous computing with domain-specific architectures (DSAs) brings…

Deep learning for medical imaging is hampered by task-specific models that lack generalizability and prognostic capabilities, while existing 'universal' approaches suffer from simplistic conditioning and poor medical semantic understanding.…

Stacked intelligent metasurfaces (SIMs) have recently gained attention as a paradigm for wave-domain signal processing with reduced reliance on costly radio-frequency (RF) chains. However, conventional SIMs rely on uniform inter-layer…

For combinatorial optimization problems, model-based approaches such as mixed-integer programming (MIP) and constraint programming (CP) aim to decouple modeling and solving a problem: the 'holy grail' of declarative problem solving. We…

Porous materials -- natural or engineered -- often exhibit dual pore-network structures that govern processes such as mineral exploration and hydrocarbon recovery from tight shales. Double porosity/permeability (DPP) mathematical models…

Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However, due to the randomness in the diffusion process, they often struggle with handling diverse low-level tasks that require details…

CubeSats require robust OBDH solutions in harsh environments. The Demoiselle OBC, featuring a radiation-tolerant APSoC and layered FSW, supports reuse, in-orbit updates, and secure operations. To be validated through ITASAT2 and SelenITA,…

Daisy (Data Analysis Integrated Software System) has been designed for the analysis and visualization of the X-ray experiments. To address an extensive range of Chinese radiation facilities community's requirements from purely algorithmic…

Many quantum computing platforms are based on a two-dimensional physical layout. Here we explore a concept called looped pipelines which permits one to obtain many of the advantages of a 3D lattice while operating a strictly 2D device. The…

Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task…