GD
Guiguang Ding
cs.CVcs.AIcs.LGcs.CLstat.MLcs.MMAlgorithmscs.HCNeural Networks, ComputerSemantics
On Valency
published · living versionsW_yvyqewe8·v1 · currentpublished
ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer
with Wenxi Li, Jingchen Huang, Chenyang Lyu, Moran Liu +2
1 version
W_u5xhxkp5·v1published
Preprints & journals
110 papers in the corpus · 2016–2026PoSTCache: From Forecasting to Postdictive Smoothing for Revisable Diffusion Caching2610.25664v1 · Liwei Lan, Hui Chen, Jungong Han et al.2026 · 0 citationsarXivon Valency
What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle2610.04303v1 · Peilin Wang, Feng Shiyang, Hongfu Gao et al.2026 · 0 citationsarXiv
Motif-Based Hypergraph Representation Learning: Transductive and Inductive Inference for Gene Regulatory Networks.42024938 · Wu, Songyang, Tang, Mingjing, Zi, Tong et al.2026 · 1 citationIEEE transactions on neural networks and learning systems. 2026;37(10):5657-5671
Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models2608.25653v1 · Yiwen Liang, Hui Chen, Yizhe Xiong et al.2026 · 0 citationsarXiv
PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies2608.15285v1 · Yufei Guo, Yinan Wu, Haoran Duan et al.2026 · 0 citationsarXiv
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs2606.23063v1 · Chuangxin Zhao, Canran Xiao, Siyuan Ma et al.2026 · 0 citationsarXiv
DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Models2606.16601v1 · Dingrong Wang, Xian Tao, Zhen Qu et al.2026 · 0 citationsarXiv
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing2605.17447v1 · Zihan Tang, Leqi Shen, Hui Chen et al.2026 · 0 citationsarXiv
CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension2602.19091v1 · Lihao Liu, Yan Wang, Biao Yang et al.2026 · 0 citationsarXiv
CAIT: Triple-Win Compression Toward High Accuracy, Fast Inference, and Favorable Transferability for ViTs.41032537 · Wang, Ao, Chen, Hui, Lin, Zijia et al.2026 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(2):1373-1389
Fixing Background Misclassification in Few-Shot Object Detection via Product of Experts.41105543 · Ong, Ding Sheng, Liu, Yi, Shang, Changjing et al.2026 · 8 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(2):1825-1841
YOLOA: Real-Time Affordance Detection via LLM Adapter2512.03418v1 · Yuqi Ji, Junjie Ke, Lihuo He et al.2025 · 0 citationsarXiv
OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving2511.21862v1 · Siyu Wu, Zihan Tang, Yuting Zeng et al.2025 · 0 citationsarXiv
Tracking and Segmenting Anything in Any Modality2511.19475v1 · Tianlu Zhang, Qiang Zhang, Guiguang Ding et al.2025 · 0 citationsarXiv
RepAttn3D: Re-parameterizing 3D attention with spatiotemporal augmentation for video understanding.41275666 · Lu, Xiusheng, Cheng, Lechao, Zhao, Sicheng et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;195:108313
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning2510.19183v1 · Fengyuan Sun, Hui Chen, Xinhao Xu et al.2025 · 0 citationsarXiv
Temporal Modeling With Frozen Vision-Language Foundation Models for Parameter-Efficient Text-Video Retrieval.40924521 · Shen, Leqi, Hao, Tianxiang, He, Tao et al.2025 · 3 citationsIEEE transactions on neural networks and learning systems. 2025;36(10):17527-17540
DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup2508.13560v2 · Zhen Qu, Xian Tao, Xinyi Gong et al.2025 · 4 citationsarXiv
Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations2507.09500v2 · Yiwen Liang, Hui Chen, Yizhe Xiong et al.2025 · 1 citationarXiv
SC: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models2506.14158v1 · Tao He, Guang Huang, Yu Yang et al.2025 · 0 citationsarXiv
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval2506.08887v1 · Leqi Shen, Guoqiang Gong, Tianxiang Hao et al.2025 · 8 citationsarXiv
Fast Quiet-STaR: Thinking Without Thought Tokens2505.17746v2 · Wei Huang, Yizhe Xiong, Xin Ye et al.2025 · 0 citationsarXiv
LSNet: See Large, Focus Small2503.23135v1 · Ao Wang, Hui Chen, Zijia Lin et al.2025 · 106 citationsarXiv
FastVID: Dynamic Density Pruning for Fast Video Large Language Models2503.11187v3 · Leqi Shen, Guoqiang Gong, Tao He et al.2025 · 7 citationsarXiv
LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs2503.11205v1 · Leqi Shen, Tao He, Guoqiang Gong et al.2025 · 0 citationsarXiv
Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection2503.10080v3 · Zhen Qu, Xian Tao, Xinyi Gong et al.2025 · 26 citationsarXiv
YOLOE: Real-Time Seeing Anything2503.07465v2 · Ao Wang, Lihao Liu, Hui Chen et al.2025 · 68 citationsarXiv
Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation.40030788 · Feng, Yifan, Huang, Jiangang, Du, Shaoyi et al.2025 · 401 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(4):2388-2401
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs2502.12455v3 · Minxuan Lv, Zhenpeng Su, Leiyu Pan et al.2025 · 0 citationsarXiv
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts2502.12928v1 · Leiyu Pan, Zhenpeng Su, Minxuan Lv et al.2025 · 0 citationsarXiv
UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs2502.00439v2 · Yizhe Xiong, Wei Huang, Xin Ye et al.2025 · 0 citationsarXiv
Source-Free Object Detection With Detection Transformer.40956712 · Yao, Huizai, Zhao, Sicheng, Lu, Shuo et al.2025 · 8 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;34:5948-5963
DAR-Prompt: Dynamic Regulation in Prompt Tuning for Multi-Label Zero-Shot Learning.41182924 · Liang, Yiwen, Chen, Hui, Lin, Zijia et al.2025 · 1 citationIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;34:7697-7711
YOLO-UniOW: Efficient Universal Open-World Object Detection2412.20645v1 · Lihao Liu, Juexiao Feng, Hui Chen et al.2024 · 1 citationarXiv
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models2412.07171v1 · Haoran Lian, Junmin Chen, Wei Huang et al.2024 · 1 citationarXiv
[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs2412.05819v1 · Ao Wang, Fengyuan Sun, Hui Chen et al.2024 · 0 citationsarXiv
Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning2411.17217v4 · Hui-Yue Yang, Hui Chen, Ao Wang et al.2024 · 4 citationsarXiv
HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator2411.17261v2 · Fan Yang, Ru Zhen, Jianing Wang et al.2024 · 7 citationsarXiv
LBPE: Long-token-first Tokenization to Improve Large Language Models2411.05504v1 · Haoran Lian, Yizhe Xiong, Zijia Lin et al.2024 · 1 citationarXiv
Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN.37824319 · Hao, Tianxiang, Ding, Xiaohan, Han, Jungong et al.2024 · 16 citationsIEEE transactions on neural networks and learning systems. 2024;35(11):16831-16844
CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts2410.16077v3 · Zhenpeng Su, Xing Wu, Zijia Lin et al.2024 · 1 citationarXiv
Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection2409.06285v1 · Hui-Yue Yang, Hui Chen, Lihao Liu et al.2024 · 4 citationsarXiv
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval2409.01156v2 · Leqi Shen, Tianxiang Hao, Tao He et al.2024 · 0 citationsarXiv
LLMI3D: MLLM-based 3D Perception from a Single 2D Image2408.07422v2 · Fan Yang, Sicheng Zhao, Yanhao Zhang et al.2024 · 5 citationsarXiv
Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence2407.18899v1 · Mengyao Lyu, Tianxiang Hao, Xinhao Xu et al.2024 · 4 citationsarXiv
VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation2407.12276v1 · Zhen Qu, Xian Tao, Mukesh Prasad et al.2024 · 62 citationsarXiv
Quantized Prompt for Efficient Generalization of Vision-Language Models2407.10704v2 · Tianxiang Hao, Xiaohan Ding, Juexiao Feng et al.2024 · 4 citationsarXiv
MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts2407.09816v4 · Zhenpeng Su, Zijia Lin, Xue Bai et al.2024 · 1 citationarXiv
More is Better: Deep Domain Adaptation with Multiple Sources2405.00749v1 · Sicheng Zhao, Hui Chen, Hu Huang et al.2024 · 8 citationsarXiv
Temporal Scaling Law for Large Language Models2404.17785v4 · Yizhe Xiong, Xiansheng Chen, Xin Ye et al.2024 · 2 citationsarXiv
Career total: 297 works. 110 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.