Search Results for author: Quan Chen

Found 53 papers, 14 papers with code

Efficient Unified Caching for Accelerating Heterogeneous AI Workloads

no code implementations14 Jun 2025 Tianze Wang, Yifei Liu, Chen Chen, Pengfei Zuo, Jiawei Zhang, Qizhen Weng, Yin Chen, Zhenhua Han, Jieru Zhao, Quan Chen, Minyi Guo

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access.

Management

Advancing LLM Safe Alignment with Safety Representation Ranking

no code implementations21 May 2025 Tianqi Du, Zeming Wei, Quan Chen, Chenheng Zhang, Yisen Wang

The rapid advancement of large language models (LLMs) has demonstrated milestone success in a variety of tasks, yet their potential for generating harmful content has raised significant safety concerns.

VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control

no code implementations20 Apr 2025 Lifeng Lin, Rongfeng Lu, Quan Chen, Haofan Ren, Ming Lu, Yaoqi Sun, Chenggang Yan, Anke Xue

Recently, many methods based on the 3D Gaussian Splatting (3DGS) framework have been proposed to address sparse-view 3D reconstruction.

3DGS 3D Reconstruction +2

A Language Vision Model Approach for Automated Tumor Contouring in Radiation Oncology

no code implementations19 Mar 2025 Yi Luo, Hamed Hooshangnejad, Xue Feng, Gaofeng Huang, Xiaojian Chen, Rui Zhang, Quan Chen, Wil Ngwa, Kai Ding

Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs to improve contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation, reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVMs hallucinations with ablation study, and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges.

Descriptive

From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval

no code implementations18 Feb 2025 Jian Jia, Jingtong Gao, Ben Xue, Junhao Wang, Qingpeng Cai, Quan Chen, Xiangyu Zhao, Peng Jiang, Kun Gai

Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs).

Information Retrieval multimodal generation +2

Relative Distance Guided Dynamic Partition Learning for Scale-Invariant UAV-View Geo-Localization

no code implementations16 Dec 2024 Quan Chen, Tingyu Wang, Rongfeng Lu, Bolun Zheng, Zhedong Zheng, Chenggang Yan

Specifically, we propose a distance guided dynamic partition learning strategy~(DGDPL), consisting of a square partition strategy and a distance-guided adjustment strategy.

geo-localization

Text-Video Multi-Grained Integration for Video Moment Montage

no code implementations12 Dec 2024 Zhihui Yin, Ye Ma, Xipeng Cao, Bo wang, Quan Chen, Peng Jiang

The proliferation of online short video platforms has driven a surge in user demand for short video editing.

Sentence Video Editing

SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization

no code implementations11 Dec 2024 Zhentao Tan, Ben Xue, Jian Jia, Junhao Wang, Wencai Ye, Shaoyun Shi, MingJie Sun, Wenjin Wu, Quan Chen, Peng Jiang

SweetTokenizer achieves comparable video reconstruction fidelity with only \textbf{25\%} of the tokens used in previous state-of-the-art video tokenizers, and boost video generation results by \textbf{32. 9\%} w. r. t gFVD.

Image Reconstruction Representation Learning +2

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads

no code implementations28 Nov 2024 Siqi Kou, Jiachun Jin, Zhihong Liu, Chang Liu, Ye Ma, Jian Jia, Quan Chen, Peng Jiang, Zhijie Deng

We introduce Orthus, an autoregressive (AR) transformer that excels in generating images given textual prompts, answering questions based on visual inputs, and even crafting lengthy image-text interleaved contents.

Language Modeling Language Modelling +3

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy

no code implementations23 Nov 2024 Te Yang, Jian Jia, Xiangyu Zhu, Weisong Zhao, Bo wang, Yanhua Cheng, Yan Li, Shengyuan Liu, Quan Chen, Peng Jiang, Kun Gai, Zhen Lei

In this paper, we propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap between MLLMs and LLMs by inhibiting the influence of irrelevant visual tokens during content generation, increasing the instruction-following ability of the MLLMs while retaining their multimodal understanding capacity.

Instruction Following MME +2

LiTformer: Efficient Modeling and Analysis of High-Speed Link Transmitters Using Non-Autoregressive Transformer

no code implementations18 Nov 2024 Songyu Sun, Xiao Dong, Yanliang Sha, Quan Chen, Cheng Zhuo

High-speed serial links are fundamental to energy-efficient and high-performance computing systems such as artificial intelligence, 5G mobile and automotive, enabling low-latency and high-bandwidth communication.

Decoder

A QoE-Aware Split Inference Accelerating Algorithm for NOMA-based Edge Intelligence

no code implementations25 Sep 2024 Xin Yuan, Ning li, Quan Chen, Wenchao Xu, Zhaoxin Zhang, Song Guo

Thus, the model split inference is proposed to improve the performance of edge intelligence, in which the AI model is divided into different sub models and the resource-intensive sub model is offloaded to edge server wirelessly for reducing resource requirements and inference latency.

Whole Heart Perfusion with High-Multiband Simultaneous Multislice Imaging via Linear Phase Modulated Extended Field of View (SMILE)

1 code implementation6 Sep 2024 Shen Zhao, Junyu Wang, Xitong Wang, Sizhuo Liu, Quan Chen, Kevin Kai Li, Yoo Jin Lee, Michael Salerno

(5-point Likert Scale) Conclusion: The theoretical derivation and experimental results validate the SMILE's improved performance at high acceleration and MB as compared to the existing 2D CAIPI SMS acquisition and reconstruction techniques for first-pass myocardial perfusion imaging.

D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching

no code implementations23 Aug 2024 Jingyu Liu, Minquan Wang, Ye Ma, Bo wang, Aozhu Chen, Quan Chen, Peng Jiang, Xirong Li

Previous studies about adding SFX to videos perform video to SFX matching at a holistic level, lacking the ability of adding SFX to a specific moment.

Highlight Detection Moment Retrieval

ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval

no code implementations6 Aug 2024 Ruixiang Zhao, Jian Jia, Yan Li, Xuehan Bai, Quan Chen, Han Li, Peng Jiang, Xirong Li

While Automatic Speech Recognition (ASR) text derived from the short or live-stream videos is readily accessible, how to de-noise the excessively noisy text for multimodal representation learning is mostly untouched.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval

1 code implementation23 Jul 2024 Xiaowan Hu, Yiyi Chen, Yan Li, Minquan Wang, Haoqian Wang, Quan Chen, Han Li, Peng Jiang

The LPR task encompasses three primary dilemmas in real-world scenarios: 1) the recognition of intended products from distractor products present in the background; 2) the video-image heterogeneity that the appearance of products showcased in live streams often deviates substantially from standardized product images in stores; 3) there are numerous confusing products with subtle visual nuances in the shop.

Retrieval

A Codesign of Scheduling and Parallelization for Large Model Training in Heterogeneous Clusters

no code implementations24 Mar 2024 Chunyu Xue, Weihao Cui, Han Zhao, Quan Chen, Shulai Zhang, Pengyu Yang, Jing Yang, Shaobo Li, Minyi Guo

The exponentially enlarged scheduling space and ever-changing optimal parallelism plan from adaptive parallelism together result in the contradiction between low-overhead and accurate performance data acquisition for efficient cluster scheduling.

Scheduling

SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization

1 code implementation7 Mar 2024 Quan Chen, Tingyu Wang, Zihao Yang, Haoran Li, Rongfeng Lu, Yaoqi Sun, Bolun Zheng, Chenggang Yan

We propose a dense partition strategy (DPS), dividing the image into multiple parts to explore contextual information while explicitly maintaining the global structure.

geo-localization Part-based Representation Learning

Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning

1 code implementation1 Jan 2024 Kaibin Tian, Yanhua Cheng, Yi Liu, Xinglin Hou, Quan Chen, Han Li

To address this issue, we adopt multi-granularity visual feature learning, ensuring the model's comprehensiveness in capturing visual content features spanning from abstract to detailed levels during the training phase.

Representation Learning Retrieval +3

Mobility and Cost Aware Inference Accelerating Algorithm for Edge Intelligence

no code implementations27 Dec 2023 Xin Yuan, Ning li, Kang Wei, Wenchao Xu, Quan Chen, Hao Chen, Song Guo

The model segmentation without user mobility has been investigated deeply by previous works.

Segmentation

STAG: Enabling Low Latency and Low Staleness of GNN-based Services with Dynamic Graphs

no code implementations27 Sep 2023 Jiawen Wang, Quan Chen, Deze Zeng, Zhuo Song, Chen Chen, Minyi Guo

With the collaborative serving mechanism, only part of node representations are updated during the update phase, and the final representations are calculated in the inference phase.

Cross-Domain Product Representation Learning for Rich-Content E-Commerce

1 code implementation ICCV 2023 Xuehan Bai, Yan Li, Yanhua Cheng, Wenjie Yang, Quan Chen, Han Li

It is the first dataset to cover product pages, short videos, and live streams simultaneously, providing the basis for establishing a unified product representation across different media domains.

Representation Learning

Cross-view Semantic Alignment for Livestreaming Product Recognition

1 code implementation ICCV 2023 Wenjie Yang, Yiyi Chen, Yan Li, Yanhua Cheng, Xudong Liu, Quan Chen, Han Li

Moreover, a cRoss-vIew semantiC alignmEnt (RICE) model is proposed to learn discriminative instance features from the image and video views of the products.

Contrastive Learning Diversity

Non-line-of-sight reconstruction via structure sparsity regularization

no code implementations5 Aug 2023 Duolan Huang, Quan Chen, Zhun Wei, Rui Chen

Subsequently, the reconstruction is achieved by optimizing a directional albedo model with SS regularization using fast iterative shrinkage-thresholding algorithm.

Autonomous Driving Denoising

AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs

no code implementations27 May 2023 Yangjie Zhou, Yaoxu Song, Jingwen Leng, Zihan Liu, Weihao Cui, Zhendong Zhang, Cong Guo, Quan Chen, Li Li, Minyi Guo

Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.

DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization

1 code implementation11 Jul 2022 Ben Xue, Shenghui Ran, Quan Chen, Rongfei Jia, Binqiang Zhao, Xing Tang

Image color harmonization algorithm aims to automatically match the color distribution of foreground and background images captured in different conditions.

Image Harmonization

SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences

no code implementations29 Jun 2022 Guan Shen, Jieru Zhao, Quan Chen, Jingwen Leng, Chao Li, Minyi Guo

However, the quadratic complexity of self-attention w. r. t the sequence length incurs heavy computational and memory burdens, especially for tasks with long sequences.

Multilayer Perceptron Based Stress Evolution Analysis under DC Current Stressing for Multi-segment Wires

no code implementations17 May 2022 Tianshu Hou, Peining Zhen, Ngai Wong, Quan Chen, Guoyong Shi, Shuqi Wang, Hai-Bao Chen

Electromigration (EM) is one of the major concerns in the reliability analysis of very large scale integration (VLSI) systems due to the continuous technology scaling.

A Space-Time Neural Network for Analysis of Stress Evolution under DC Current Stressing

no code implementations29 Mar 2022 Tianshu Hou, Ngai Wong, Quan Chen, Zhigang Ji, Hai-Bao Chen

The electromigration (EM)-induced reliability issues in very large scale integration (VLSI) circuits have attracted increased attention due to the continuous technology scaling.

Boosting Image Outpainting with Semantic Layout Prediction

no code implementations18 Oct 2021 Ye Ma, Jin Ma, Min Zhou, Quan Chen, Tiezheng Ge, Yuning Jiang, Tong Lin

Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts.

Image Outpainting Prediction +1

Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection

no code implementations8 Sep 2021 Shulai Zhang, Zirui Li, Quan Chen, Wenli Zheng, Jingwen Leng, Minyi Guo

Federated learning (FL) is a distributed machine learning paradigm that allows clients to collaboratively train a model over their own local data.

Federated Learning

FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation

1 code implementation15 Feb 2021 Chaofan Tao, Rui Lin, Quan Chen, Zhaoyang Zhang, Ping Luo, Ngai Wong

Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e. g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy.

Neural Network Compression Quantization

Federated Learning on Non-IID Data Silos: An Experimental Study

4 code implementations3 Feb 2021 Qinbin Li, Yiqun Diao, Quan Chen, Bingsheng He

We find that non-IID does bring significant challenges in learning accuracy of FL algorithms, and none of the existing state-of-the-art FL algorithms outperforms others in all cases.

BIG-bench Machine Learning Federated Learning

Edge Computing Assisted Autonomous Flight for UAV: Synergies between Vision and Communications

no code implementations10 Dec 2020 Quan Chen, Hai Zhu, Lei Yang, Xiaoqian Chen, Sofie Pollin, Evgenii Vinogradov

By proposing a framework of Edge Computing Assisted Autonomous Flight (ECAAF), we illustrate that vision and communications can interact with and assist each other with the aid of edge computing and offloading, and further speed up the UAV mission completion.

Edge-computing Trajectory Planning Networking and Internet Architecture Robotics Systems and Control Systems and Control

How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention

no code implementations COLING 2020 Yue Guan, Jingwen Leng, Chao Li, Quan Chen, Minyi Guo

Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.

Clustering

How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention

no code implementations2 Nov 2020 Yue Guan, Jingwen Leng, Chao Li, Quan Chen, Minyi Guo

Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.

Clustering

Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration

no code implementations18 Feb 2020 Cong Guo, Yangjie Zhou, Jingwen Leng, Yuhao Zhu, Zidong Du, Quan Chen, Chao Li, Bin Yao, Minyi Guo

We propose Simultaneous Multi-mode Architecture (SMA), a novel architecture design and execution model that offers general-purpose programmability on DNN accelerators in order to accelerate end-to-end applications.

Adversarial Defense Through Network Profiling Based Path Extraction

no code implementations CVPR 2019 Yuxian Qiu, Jingwen Leng, Cong Guo, Quan Chen, Chao Li, Minyi Guo, Yuhao Zhu

Recently, researchers have started decomposing deep neural network models according to their semantics or functions.

Adversarial Defense

Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure

no code implementations6 Mar 2019 Huitong Pan, Yushan Feng, Quan Chen, Craig Meyer, Xue Feng

Using PROMISE-12 data, we demonstrated the robustness of the two-stage model and showed high correlation of the proposed variable-input based uncertainty measures with GT-based performance.

Data Augmentation Segmentation

Effective Path: Know the Unknowns of Neural Network

no code implementations27 Sep 2018 Yuxian Qiu, Jingwen Leng, Yuhao Zhu, Quan Chen, Chao Li, Minyi Guo

Despite their enormous success, there is still no solid understanding of deep neural network’s working mechanism.

Semantic Human Matting

2 code implementations5 Sep 2018 Quan Chen, Tiezheng Ge, Yanyu Xu, Zhiqiang Zhang, Xinxin Yang, Kun Gai

SHM is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks.

Image Matting

DLFuzz: Differential Fuzzing Testing of Deep Learning Systems

1 code implementation28 Aug 2018 Jianmin Guo, Yu Jiang, Yue Zhao, Quan Chen, Jiaguang Sun

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars.

Software Engineering

Deep joint rain and haze removal from single images

no code implementations21 Jan 2018 Liang Shen, Zihan Yue, Quan Chen, Fan Feng, Jie Ma

On the other hand, the accumulation of rain streaks from long distance makes the rain image look like haze veil.

Rain Removal

MSR-net:Low-light Image Enhancement Using Deep Convolutional Network

no code implementations7 Nov 2017 Liang Shen, Zihan Yue, Fan Feng, Quan Chen, Shihao Liu, Jie Ma

In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed.

Low-Light Image Enhancement

Cannot find the paper you are looking for? You can Submit a new open access paper.