相关论文: TTP: A Hardware-Efficient Design for Precise Prefe…

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Modeling data sharing in GPU programs is a challenging task because of the massive parallelism and complex data sharing patterns provided by GPU architectures. Better GPU caching efficiency can be achieved through careful task scheduling…

Packing for Supervised Fine-Tuning (SFT) in autoregressive models involves concatenating data points of varying lengths until reaching the designed maximum length to facilitate GPU processing. However, randomly concatenating data points can…

The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight…

To support the growing demands of neuroscience applications, researchers are transitioning to cloud computing for its scalable, robust and elastic infrastructure. Nevertheless, large datasets residing in object stores may result in…

Triangle Counting (TC) is a procedure that involves enumerating the number of triangles within a graph. It has important applications in numerous fields, such as social or biological network analysis and network security. TC is a…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…

Radio frequency (RF) propagation modeling poses unique electromagnetic simulation challenges. While recent neural representations have shown success in visible spectrum rendering, the fundamentally different scales and physics of RF signals…

Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamental bottleneck. Current tactile simulations suffer from a persistent dilemma: simplified…

3D Gaussian splatting has been widely adopted as a 3D representation for novel-view synthesis, relighting, and 3D generation tasks. It delivers realistic and detailed results through a collection of explicit 3D Gaussian primitives, each…

Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive…

Virtual Reality (VR) applications require high data rate for a high-quality immersive experience, in addition to low latency to avoid dizziness and motion sickness. One of the key wireless VR challenges is providing seamless connectivity…

Transfer entropy (TE) is an information theoretic measure that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-world applications. This work proposes Transfer Entropy…

Temporal graph representation learning (TGRL) is essential for modeling dynamic systems in real-world networks. However, traditional TGRL methods, despite their effectiveness, often face significant computational challenges and inference…

Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due…

This paper considers the problem of retrieving an object from many tightly packed objects using a combination of robotic pushing and grasping actions. Object retrieval in dense clutter is an important skill for robots to operate in…

We introduce the transport-and-pack(TAP) problem, a frequently encountered instance of real-world packing, and develop a neural optimization solution based on reinforcement learning. Given an initial spatial configuration of boxes, we seek…

GPUs exploit a high degree of thread-level parallelism to hide long-latency stalls. Due to the heterogeneous compute requirements of different applications, there is a growing need to share the GPU across multiple applications in…

Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In this paper, we explore how synthetic models alleviate the…

Concurrent processing of multiple autonomous driving 3D perception tasks within the same spatiotemporal scene poses a significant challenge, in particular due to the computational inefficiencies and feature competition between tasks when…