相关论文: Cornserve: A Distributed Serving System for Any-to…

Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce \textbf{AnyView}, a…

Multi-modal remote sensing imagery provides complementary observations of the same geographic scene, yet such observations are frequently incomplete in practice. Existing cross-modal translation methods treat each modality pair as an…

While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing…

Distributed computing remains inaccessible to a large number of users, in spite of many open source platforms and extensive commercial offerings. While distributed computation frameworks have moved beyond a simple map-reduce model, many…

We introduce OneDiffusion, a versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. It enables conditional generation from inputs such as text, depth, pose,…

To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a…

Partitioning a graph into balanced blocks such that few edges run between blocks is a key problem for large-scale distributed processing. A current trend for partitioning huge graphs are streaming algorithms, which use low computational…

Multimodal datasets contain an enormous amount of relational information, which grows exponentially with the introduction of new modalities. Learning representations in such a scenario is inherently complex due to the presence of multiple…

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…

Monolithic software encapsulates all functional capabilities into a single deployable unit. But managing it becomes harder as the demand for new functionalities grow. Microservice architecture is seen as an alternate as it advocates…

Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising…

With the widespread adoption of large multimodal models, efficient inference across text, image, audio, and video modalities has become critical. However, existing multimodal inference systems typically employ monolithic architectures that…

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

Style transfer aims to render the style of a given image for style reference to another given image for content reference, and has been widely adopted in artistic generation and image editing. Existing approaches either apply the holistic…

Diffusion pipelines, renowned for their powerful visual generation capabilities, have seen widespread adoption in generative vision tasks (e.g., text-to-image/video). These pipelines typically follow an encode--diffuse--decode three-stage…

This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabilities. HyperStream overcomes the limitations of other…

Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner.…

Data distribution across different facilities offers benefits such as enhanced resource utilization, increased resilience through replication, and improved performance by processing data near its source. However, managing such data is…

In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any interleaved multimedia form. This capability defines the goal…

Diffusion models have demonstrated remarkable performance in generating unimodal data across various tasks, including image, video, and text generation. On the contrary, the joint generation of multimodal data through diffusion models is…