相关论文: Analytical Heterogeneous Die-to-Die 3D Placement w…

In our previous work [2], we introduced a hardware- and power-efficient architecture for hybrid digital-analog (HDA) multiuser MIMO (MU-MIMO) based on stacking identical basic modules. Each module consists of a small active multi-antenna…

We present a visual localization framework based on novel deep attention aware features for autonomous driving that achieves centimeter level localization accuracy. Conventional approaches to the visual localization problem rely on…

The solidification and macro-segregation problem involving unsteady multi-physics and multi-phase fields is typically a complex process with mass, momentum, heat, and species transfers among solid, mushy, and liquid phase regions. The…

Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabulary of visual tokens. This conventional approach treats tokens…

This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. Our approach stems from the observation that existing methods for hierarchical representation…

3D-Integration is a promising technology towards higher interconnect densities and shorter wiring lengths between multiple chip stacks, thus achieving a very high performance level combined with low power consumption. This technology also…

3D pre-training is crucial to 3D perception tasks. Nevertheless, limited by the difficulties in collecting clean and complete 3D data, 3D pre-training has persistently faced data scaling challenges. In this work, we introduce a novel…

3D image segmentation plays an important role in biomedical image analysis. Many 2D and 3D deep learning models have achieved state-of-the-art segmentation performance on 3D biomedical image datasets. Yet, 2D and 3D models have their own…

We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent…

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and…

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in the computer vision community. However, most algorithms are designed for faces in small to medium poses…

We propose a hierarchical architecture for efficiently computing high-quality solutions to structured mixed-integer programs (MIPs). To reduce computational effort, our approach decouples the original problem into a higher level problem and…

The rapid growth of deep learning models has increased the demand for efficient distributed training strategies. Fully sharded approaches like ZeRO-3 and FSDP partition model parameters across GPUs and apply optimizations such as…

Deep neural networks have seen tremendous success for different modalities of data including images, videos, and speech. This success has led to their deployment in mobile and embedded systems for real-time applications. However, making…

Face analysis tasks have a wide range of applications, but the universal facial representation has only been explored in a few works. In this paper, we explore high-performance pre-training methods to boost the face analysis tasks such as…

Addressing missing modalities is an important challenge in multimodal image analysis and often relies on complex architectures that do not transfer easily to different datasets without architectural modifications or hyperparameter tuning.…

In this paper, we present a solution to the industrial challenge put forth by ARM in 2022. We systematically analyze the effect of shared resource contention to an augmented reality head-up display (AR-HUD) case-study application of the…

Nanoindentation is vital for probing mechanical properties, yet traditional grid-based workflows are inefficient for targeting specific microstructural features. We present an automated nanoindentation framework that integrates machine…

Recent top-performing temporal 3D detectors based on Lidars have increasingly adopted region-based paradigms. They first generate coarse proposals, followed by encoding and fusing regional features. However, indiscriminate sampling and…

In this paper, we adopt 3D Convolutional Neural Networks to segment volumetric medical images. Although deep neural networks have been proven to be very effective on many 2D vision tasks, it is still challenging to apply them to 3D tasks…