1.7k citations · 1.8k across the 19 of their papers we have counts for
20 papers
DUET4D: Self-Corrective Coupled Guidance for Sparse-View 4D Reconstruction
Beizhen Zhao, Nanjie Yao, Boyi Fu +4
Sparse-view 4D reconstruction is highly under-constrained when only a few cameras are available. Generative priors can recover missing appearances, but video models are computation…
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
Xiang Liu, Shimiao Yuan, Zhenheng Tang +5
LLM inference is still evaluated mainly as a model or software problem: accuracy, latency, throughput, and hardware utilization. This is incomplete. At deployment scale, the releva…
SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation
Song Tang, Kaiyong Zhao, Yuliang Li +5
Automatically generating interactive 3D indoor scenes from natural language is crucial for virtual reality, gaming, and embodied AI. However, existing LLM-based approaches often su…
EdgeFM: Efficient Edge Inference for Vision-Language Models
Mengling Deng, Yuanpeng Chen, Sheng Yang +12
Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for determin…
RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories
Qingsong Yan, Qiang Wang, Kaiyong Zhao +4
Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on ac…
SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
Qingsong Yan, Qiang Wang, Kaiyong Zhao +4
Due to the rapid development of panorama cameras, the task of estimating panorama depth has attracted significant attention from the computer vision community, especially in applic…
FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression
Zhenheng Tang, Xueze Kang, Yiming Yin +11
To alleviate hardware scarcity in training large deep neural networks (DNNs), particularly large language models (LLMs), we present FusionLLM, a decentralized training system desig…
CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning
Qingsong Yan, Qiang Wang, Kaiyong Zhao +4
Neural Radiance Fields (NeRF) have demonstrated impressive performance in novel view synthesis. However, NeRF and most of its variants still rely on traditional complex pipelines t…
FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs
Zhenheng Tang, Yuxin Wang, Xin He +8
The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPU…
Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity
Qingsong Yan, Qiang Wang, Kaiyong Zhao +3
Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable. To address this…
SphereDepth: Panorama Depth Estimation from Spherical Domain
Qingsong Yan, Qiang Wang, Kaiyong Zhao +3
The panorama image can simultaneously demonstrate complete information of the surrounding environment and has many advantages in virtual tourism, games, robotics, etc. However, the…
EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching
Qiang Wang, Shaohuai Shi, Kaiyong Zhao +1
Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference spee…
FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks
Qiang Wang, Shaohuai Shi, Shizhen Zheng +2
Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better pre…
FADNet: A Fast and Accurate Network for Disparity Estimation
Qiang Wang, Shaohuai Shi, Shizhen Zheng +2
Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better pre…
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
Qiang Wang, Shizhen Zheng, Qingsong Yan +3
Indoor robotics localization, navigation, and interaction heavily rely on scene understanding and reconstruction. Compared to the monocular vision which usually does not explicitly…
Layer-wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guarantees
Shaohuai Shi, Zhenheng Tang, Qiang Wang +2
To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. Ho…
Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training
Yuxin Wang, Qiang Wang, Shaohuai Shi +4
Deep learning has become widely used in complex AI applications. Yet, training a deep neural network (DNNs) model requires a considerable amount of calculations, long running time,…
AutoML: A Survey of the State-of-the-Art
Xin He, Kaiyong Zhao, Xiaowen Chu
Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relie…
A Distributed Synchronous SGD Algorithm with Global Top- Sparsification for Low Bandwidth Networks
Shaohuai Shi, Qiang Wang, Kaiyong Zhao +4
Distributed synchronous stochastic gradient descent (S-SGD) has been widely used in training large-scale deep neural networks (DNNs), but it typically requires very high communicat…
Detecting "protein words" through unsupervised word segmentation
Wang Liang, Zhao KaiYong
Unsupervised word segmentation methods were applied to analyze the protein sequence. Protein sequences, such as 'MTMDKSELVQKA...', were used as input to these methods. Segmented 'p…