39 citations · 118 across the 21 of their papers we have counts for
21 papers
MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
Yuanteng Chen, Nanxin Zeng, Peisong Wang +9
Mixture-of-Experts Multimodal Large Language Models (MoE-MLLMs) offer remarkable performance but incur prohibitive GPU memory costs, making compression essential. Among PTQ methods…
RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI
Weifan Guan, Qinghao Hu, Huasen Xi +3
Vision-language-action (VLA) models and LLM agents have advanced rapidly, yet reliable deployment on physical robots is often hindered by an interface mismatch between agent tool A…
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
Weifan Guan, Qinghao Hu, Aosheng Li +1
Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite the…
Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation
Xingting Yao, Qinghao Hu, Fei Zhou +4
Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associat…
FastGL: A GPU-Efficient Framework for Accelerating Sampling-Based GNN Training at Large Scale
Zeyu Zhu, Peisong Wang, Qinghao Hu +3
Graph Neural Networks (GNNs) have shown great superiority on non-Euclidean graph data, achieving ground-breaking performance on various graph-related tasks. As a practical solution…
MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization
Zeyu Zhu, Fanrong Li, Gang Li +5
Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accele…
SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World
Xingting Yao, Qinghao Hu, Fei Zhou +5
In this paper, we propose SpikingNeRF, which aligns the temporal dimension of spiking neural networks (SNNs) with the radiance rays, to seamlessly accommodate SNNs to the reconstru…
: Aggregation-Aware Quantization for Graph Neural Networks
Zeyu Zhu, Fanrong Li, Zitao Mo +5
As graph data size increases, the vast latency and memory consumption during inference pose a significant challenge to the real-world deployment of Graph Neural Networks (GNNs). Wh…
DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection
Yiqun Chen, Qiang Chen, Qinghao Hu +1
Fully convolutional detectors discard the one-to-many assignment and adopt a one-to-one assigning strategy to achieve end-to-end detection but suffer from the slow convergence issu…
Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets
Xiangyu Chen, Qinghao Hu, Kaidong Li +2
Vision Transformers has demonstrated competitive performance on computer vision tasks benefiting from their ability to capture long-range dependencies with multi-head self-attentio…
PalQuant: Accelerating High-precision Networks on Low-precision Accelerators
Qinghao Hu, Gang Li, Qiman Wu +1
Recently low-precision deep learning accelerators (DLAs) have become popular due to their advantages in chip area and energy consumption, yet the low-precision quantized models on…
MixFormer: Mixing Features across Windows and Dimensions
Qiang Chen, Qiman Wu, Jian Wang +5
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs…
Soft Threshold Ternary Networks
Weixiang Xu, Xiangyu He, Tianli Zhao +3
Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency…
Architecture Aware Latency Constrained Sparse Neural Networks
Tianli Zhao, Qinghao Hu, Xiangyu He +4
Acceleration of deep neural networks to meet a specific latency constraint is essential for their deployment on mobile devices. In this paper, we design an architecture aware laten…
HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap
Xing Lan, Qinghao Hu, Qiang Chen +2
Heatmap-based regression overcomes the lack of spatial and contextual information of direct coordinate regression, and has revolutionized the task of face alignment. Yet it suffers…
Generative Zero-shot Network Quantization
Xiangyu He, Qinghao Hu, Peisong Wang +1
Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level im…
A System-Level Solution for Low-Power Object Detection
Fanrong Li, Zitao Mo, Peisong Wang +8
Object detection has made impressive progress in recent years with the help of deep learning. However, state-of-the-art algorithms are both computation and memory intensive. Though…
Compact Global Descriptor for Neural Networks
Xiangyu He, Ke Cheng, Qiang Chen +3
Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks. Yet neither stacks of convo…
Recent Advances in Efficient Computation of Deep Convolutional Neural Networks
Jian Cheng, Peisong Wang, Gang Li +2
Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems. At the same time, the computational c…
From Hashing to CNNs: Training BinaryWeight Networks via Hashing
Qinghao Hu, Peisong Wang, Jian Cheng
Deep convolutional neural networks (CNNs) have shown appealing performance on various computer vision tasks in recent years. This motivates people to deploy CNNs to realworld appli…
Quantized Convolutional Neural Networks for Mobile Devices
Jiaxiang Wu, Cong Leng, Yuhang Wang +2
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensab…