Related papers: DynaFlow: Transparent and Flexible Intra-Device Pa…

Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers…

Neuromorphic computing exhibits great potential to provide high-performance benefits in various applications beyond neural networks. However, a general-purpose program execution model that aligns with the features of neuromorphic computing…

This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow…

Applications in science and engineering often require huge computational resources for solving problems within a reasonable time frame. Parallel supercomputers provide the computational infrastructure for solving such problems. A…

Among these, D-peptides are resistant to proteolysis, exhibit greater in vivo stability, and are easier to synthesize. Despite advances in deep learning for peptide discovery, the scarcity of natural D-protein data limits the transfer of…

Serverless computing that runs functions with auto-scaling is a popular task execution pattern in the cloud-native era. By connecting serverless functions into workflows, tenants can achieve complex functionality. Prior researches adopt the…

As the need for more computing power grows, traditional methods are hitting limits. To boost performance, we're expanding Central Processing Unit (CPU) capabilities and using specialized hardware accelerators. For example, mobile devices…

Interest in deploying Deep Neural Network (DNN) inference on edge devices has resulted in an explosion of the number and types of hardware platforms to use. While the high-level programming interface, such as TensorFlow, can be readily…

There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a variety of processing units such as CPUs, GPUs, and NPUs, the…

Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the temporal domain. While recent trends shift towards multi-frame reasoning, they suffer from rapidly…

Motivated by the need for adaptive, secure and responsive scheduling in a great range of computing applications, including human-centered and time-critical applications, this paper proposes a scheduling framework that seamlessly adds…

Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the…

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…

With the growing model size, deep neural networks (DNN) are increasingly trained over massive GPU accelerators, which demands a proper parallelization plan that transforms a DNN model into fine-grained tasks and then schedules them to GPUs…

As Machine Learning (ML) gains adoption across industries and new use cases, practitioners increasingly realize the challenges around effectively developing and iterating on ML systems: reproducibility, debugging, scalability, and…

TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. TensorFlow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. It maps the nodes of…

Parallel dataflow systems have become a standard technology for large-scale data analytics. Complex data analysis programs in areas such as machine learning and graph analytics often involve control flow, i.e., iterations and branching.…

Data engineering workflows require reliable differencing across files, databases, and query outputs, yet existing tools falter under schema drift, heterogeneous types, and limited explainability. SmartDiff is a unified system that combines…

This paper introduces a novel optimization framework for deep neural network (DNN) hardware accelerators, enabling the rapid development of customized and automated design flows. More specifically, our approach aims to automate the…

Several methods exist today to accelerate Machine Learning(ML) or Deep-Learning(DL) model performance for training and inference. However, modern techniques that rely on various graph and operator parallelism methodologies rely on search…