Dong Li

72 papers A* 20A 1B 3Journal 42Unranked 6
YearRankTypeTitle / Venue / Authors
2026 A* conf
DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation.
AAAI
Jiajun Jiao, Haowei Zhu, Puyuan Yang, Jianghui Wang, Ji Liu, Ziqiong Liu, Dong Li, Yuejian Fang, Jun-Hai Yong, Bin Wang, Emad Barsoum
2026 J jnl
DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation.
CoRR
Jiajun Jiao, Haowei Zhu, Puyuan Yang, Jianghui Wang, Ji Liu, Ziqiong Liu, Dong Li, Yuejian Fang, Junhai Yong, Bin Wang, Emad Barsoum
2026 A* conf
Learnable Permutation for Structured Sparsity on Transformer Models.
AAAI
Zekai Li, Ji Liu, Guanchen Li, Yixing Xu, Ziqiong Liu, Xuanwu Yin, Dong Li, Emad Barsoum
2026 J jnl
Learnable Permutation for Structured Sparsity on Transformer Models.
CoRR
Zekai Li, Ji Liu, Guanchen Li, Yixing Xu, Ziqiong Liu, Xuanwu Yin, Dong Li, Emad Barsoum
2026 A* conf
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning.
AAAI
Huanxuan Liao, Yixing Xu, Shizhu He, Guanchen Li, Xuanwu Yin, Dong Li, Emad Barsoum, Jun Zhao, Kang Liu
2025 J jnl
AMD-Hummingbird: Towards an Efficient Text-to-Video Model.
CoRR
Takashi Isobe, He Cui, Dong Zhou, Mengmeng Ge, Dong Li, Emad Barsoum
2025 — conf
Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference.
NAACL (Long Papers)
Zeping Li, Xinlong Yang, Ziheng Gao, Ji Liu, Guanchen Li, Zhuang Liu, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum
2025 J jnl
Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models.
CoRR
Shuai Wang, Zhenhua Liu, Jiaheng Wei, Xuanwu Yin, Dong Li, Emad Barsoum
2025 A* conf
BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation.
ICML
Lian Liu, Xiandong Zhao, Guanchen Li, Dong Li, Mengdi Wang, Yinhe Han, Xiaowei Li, Ying Wang
2025 J jnl
DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models.
CoRR
Wenjin Ke, Zhe Li, Dong Li, Lu Tian, Emad Barsoum
2025 J jnl
Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates.
CoRR
Yixing Xu, Chao Li, Xuanwu Yin, Spandan Tiwari, Dong Li, Ashish Sirasao, Emad Barsoum
2025 J jnl
E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources.
CoRR
Tong Shen, Jingai Yu, Dong Zhou, Dong Li, Emad Barsoum
2025 A* conf
EGSRAL: An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene.
AAAI
Yixiong Huo, Guangfeng Jiang, Hongyang Wei, Ji Liu, Song Zhang, Han Liu, Xingliang Huang, Mingjie Lu, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
2025 J jnl
Edit as You See: Image-guided Video Editing via Masked Motion Modeling.
CoRR
Zhi-Lin Huang, Yixuan Liu, Chujun Qin, Zhongdao Wang, Dong Zhou, Dong Li, Emad Barsoum
2025 B conf
Enhancing One-Shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism.
COLING
Guanchen Li, Xiandong Zhao, Lian Liu, Zeping Li, Yixing Xu, Dong Li, Lu Tian, Jie He, Ashish Sirasao, Emad Barsoum
2025 J jnl
Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks.
CoRR
Jianghui Wang, Vinay Joshi, Saptarshi Majumder, Xu Chao, Bin Ding, Ziqiong Liu, Pratik Prabhanjan Brahma, Dong Li, Zicheng Liu, Emad Barsoum
2025 A* conf
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.
ICML
Jinze Li, Yixing Xu, Haiduo Huang, Xuanwu Yin, Dong Li, Edith C. H. Ngai, Emad Barsoum
2025 J jnl
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.
CoRR
Jinze Li, Yixing Xu, Haiduo Huang, Xuanwu Yin, Dong Li, Edith C. H. Ngai, Emad Barsoum
2025 J jnl
Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE.
CoRR
Haiduo Huang, Fuwei Yang, Zhenhua Liu, Yixing Xu, Jinze Li, Yang Liu, Xuanwu Yin, Dong Li, Pengju Ren, Emad Barsoum
2025 J jnl
Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking.
CoRR
Zirui Zheng, Takashi Isobe, Tong Shen, Xu Jia, Jianbin Zhao, Xiaomin Li, Mengmeng Ge, Baolu Li, Qinghe Wang, Dong Li, Dong Zhou, Yunzhi Zhuge, Huchuan Lu, Emad Barsoum
2025 J jnl
MSWA: Refining Local Attention with Multi-ScaleWindow Attention.
CoRR
Yixing Xu, Shivank Nag, Dong Li, Lu Tian, Emad Barsoum
2025 J jnl
MonoGS++: Fast and Accurate Monocular RGB Gaussian SLAM.
CoRR
Renwu Li, Wenjing Ke, Dong Li, Lu Tian, Emad Barsoum
2025 J jnl
PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation.
CoRR
Zihao An, Huajun Bai, Ziqiong Liu, Dong Li, Emad Barsoum
2025 J jnl
Partial Convolution Meets Visual Attention.
CoRR
Haiduo Huang, Fuwei Yang, Dong Li, Ji Liu, Lu Tian, Jinzhang Peng, Pengju Ren, Emad Barsoum
2025 A* conf
ReNeg: Learning Negative Embedding with Reward Guidance.
CVPR
Xiaomin Li, Yixuan Liu, Takashi Isobe, Xu Jia, Qinpeng Cui, Dong Zhou, Dong Li, You He, Huchuan Lu, Zhongdao Wang, Emad Barsoum
2025 J jnl
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning.
CoRR
Huanxuan Liao, Yixing Xu, Shizhu He, Guanchen Li, Xuanwu Yin, Dong Li, Emad Barsoum, Jun Zhao, Kang Liu
2025 J jnl
SpecVLM: Fast Speculative Decoding in Vision-Language Models.
CoRR
Haiduo Huang, Fuwei Yang, Zhenhua Liu, Xuanwu Yin, Dong Li, Pengju Ren, Emad Barsoum
2025 J jnl
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match.
CoRR
Jinze Li, Yixing Xu, Guanchen Li, Shuo Yang, Jinfeng Xu, Xuanwu Yin, Dong Li, Edith C. H. Ngai, Emad Barsoum
2025 J jnl
Týr-the-Pruner: Unlocking Accurate 50% Structural Pruning for LLMs via Global Sparsity Distribution Optimization.
CoRR
Guanchen Li, Yixing Xu, Zeping Li, Ji Liu, Xuanwu Yin, Dong Li, Emad Barsoum
2024 J jnl
Amphista: Accelerate LLM Inference with Bi-directional Multiple Drafting Heads in a Non-autoregressive Style.
CoRR
Zeping Li, Xinlong Yang, Ziheng Gao, Ji Liu, Zhuang Liu, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum
2024 — conf
DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models.
EMNLP (Industry Track)
Wenjing Ke, Zhe Li, Dong Li, Lu Tian, Emad Barsoum
2024 A* conf
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization.
NeurIPS
Haowei Zhu, Dehua Tang, Ji Liu, Mingjie Lu, Jintu Zheng, Jinzhang Peng, Dong Li, Yu Wang, Fan Jiang, Lu Tian, Spandan Tiwari, Ashish Sirasao, Jun-Hai Yong, Bin Wang, Emad Barsoum
2024 J jnl
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization.
CoRR
Haowei Zhu, Dehua Tang, Ji Liu, Mingjie Lu, Jintu Zheng, Jinzhang Peng, Dong Li, Yu Wang, Fan Jiang, Lu Tian, Spandan Tiwari, Ashish Sirasao, Jun-Hai Yong, Bin Wang, Emad Barsoum
2024 J jnl
EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene.
CoRR
Yixiong Huo, Guangfeng Jiang, Hongyang Wei, Ji Liu, Song Zhang, Han Liu, Xingliang Huang, Mingjie Lu, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
2024 J jnl
Enhancing One-shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism.
CoRR
Guanchen Li, Xiandong Zhao, Lian Liu, Zeping Li, Dong Li, Lu Tian, Jie He, Ashish Sirasao, Emad Barsoum
2024 A* conf
Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module.
ICML
Yixing Xu, Chao Li, Dong Li, Xiao Sheng, Fan Jiang, Lu Tian, Ashish Sirasao, Emad Barsoum
2024 J jnl
FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing.
CoRR
Zekai Li, Jintu Zheng, Ji Liu, Han Liu, Haowei Zhu, Zeping Li, Fuwei Yang, Haiduo Huang, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
2024 J jnl
Fast Occupancy Network.
CoRR
Mingjie Lu, Yuanxian Huang, Ji Liu, Xingliang Huang, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum
2024 J jnl
LADDER: An Efficient Framework for Video Frame Interpolation.
CoRR
Tong Shen, Dong Li, Ziheng Gao, Lu Tian, Emad Barsoum
2024 A conf
MonoGS++: Fast and Accurate Monocular RGB Gaussian SLAM.
BMVC
Renwu Li, Wenjing Ke, Dong Li, Lu Tian, Emad Barsoum
2024 A* conf
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion.
NeurIPS
Yixing Xu, Chao Li, Dong Li, Xiao Sheng, Fan Jiang, Lu Tian, Emad Barsoum
2024 J jnl
ReNeg: Learning Negative Embedding with Reward Guidance.
CoRR
Xiaomin Li, Yixuan Liu, Takashi Isobe, Xu Jia, Qinpeng Cui, Dong Zhou, Dong Li, You He, Huchuan Lu, Zhongdao Wang, Emad Barsoum
2024 J jnl
Sparse Laneformer.
CoRR
Ji Liu, Zifeng Zhang, Mingjie Lu, Hongyang Wei, Dong Li, Yile Xie, Jinzhang Peng, Lu Tian, Ashish Sirasao, Emad Barsoum
2024 J jnl
TernaryLLM: Ternarized Large Language Model.
CoRR
Tianqi Chen, Zhe Li, Weixiang Xu, Zeyu Zhu, Dong Li, Lu Tian, Emad Barsoum, Peisong Wang, Jian Cheng
2024 J jnl
Towards Scale-Aware Full Surround Monodepth with Transformers.
CoRR
Yuchen Yang, Xinyi Wang, Dong Li, Lu Tian, Ashish Sirasao, Xun Yang
2024 A* conf
UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer.
AAAI
Ji Liu, Dehua Tang, Yuanxian Huang, Li Zhang, Xiaocheng Zeng, Dong Li, Mingjie Lu, Jinzhang Peng, Yu Wang, Fan Jiang, Lu Tian, Ashish Sirasao
2024 J jnl
UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer.
CoRR
Ji Liu, Dehua Tang, Yuanxian Huang, Li Zhang, Xiaocheng Zeng, Dong Li, Mingjie Lu, Jinzhang Peng, Yu Wang, Fan Jiang, Lu Tian, Ashish Sirasao
2024 J jnl
XVDPU: A High-Performance CNN Accelerator on the Versal Platform Powered by the AI Engine.
ACM Trans. Reconfigurable Technol. Syst.
Xijie Jia, Yu Zhang, Guangdong Liu, Xinlin Yang, Tianyu Zhang, Jia Zheng, Dongdong Xu, Zhuohuan Liu, Mengke Liu, Xiaoyang Yan, Hong Wang, Rongzhang Zheng, Li Wang, Dong Li, Satyaprakash Pareek, Jian Weng, Lu Tian, Dongliang Xie, Hong Luo, Yi Shan
2023 A* conf
FDViT: Improve the Hierarchical Architecture of Vision Transformer.
ICCV
Yixing Xu, Chao Li, Dong Li, Xiao Sheng, Fan Jiang, Lu Tian, Ashish Sirasao
2022 B conf
A-U3D: A Unified 2D/3D CNN Accelerator on the Versal Platform for Disparity Estimation.
FPL
Tianyu Zhang, Dong Li, Hong Wang, Yunzhi Li, Xiang Ma, Wei Luo, Yu Wang, Yang Huang, Yi Li, Yu Zhang, Xinlin Yang, Xijie Jia, Qiang Lin, Lu Tian, Fan Jiang, Dongliang Xie, Hong Luo, Yi Shan
2022 A* conf
Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving.
AAAI
Li Wang, Dong Li, Han Liu, Jinzhang Peng, Lu Tian, Yi Shan
2022 A* conf
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification.
CVPR
Haowei Zhu, Wenjing Ke, Dong Li, Ji Liu, Lu Tian, Yi Shan
2022 J jnl
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification.
CoRR
Haowei Zhu, Wenjing Ke, Dong Li, Ji Liu, Lu Tian, Yi Shan
2022 A* conf
Dynamic Sparse R-CNN.
CVPR
Qinghang Hong, Fengming Liu, Dong Li, Ji Liu, Lu Tian, Yi Shan
2022 J jnl
Dynamic Sparse R-CNN.
CoRR
Qinghang Hong, Fengming Liu, Dong Li, Ji Liu, Lu Tian, Yi Shan
2022 — conf
Efficient Image Super-Resolution with Collapsible Linear Blocks.
CVPR Workshops
Li Wang, Dong Li, Lu Tian, Yi Shan
2022 J jnl
HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection.
CoRR
Ji Liu, Dong Li, Zekun Li, Han Liu, Wenjing Ke, Lu Tian, Yi Shan
2021 J jnl
Cross-Dataset Collaborative Learning for Semantic Segmentation.
CoRR
Li Wang, Dong Li, Yousong Zhu, Lu Tian, Yi Shan
2021 A* conf
Improving Low-Precision Network Quantization via Bin Regularization.
ICCV
Tiantian Han, Dong Li, Ji Liu, Lu Tian, Yi Shan
2021 A* conf
RankDetNet: Delving Into Ranking Constraints for Object Detection.
CVPR
Ji Liu, Dong Li, Rongzhang Zheng, Lu Tian, Yi Shan
2021 A* conf
Towards Discriminative Representation Learning for Unsupervised Person Re-identification.
ICCV
Takashi Isobe, Dong Li, Lu Tian, Weihua Chen, Yi Shan, Shengjin Wang
2021 J jnl
Towards Discriminative Representation Learning for Unsupervised Person Re-identification.
CoRR
Takashi Isobe, Dong Li, Lu Tian, Weihua Chen, Yi Shan, Shengjin Wang
2020 A* conf
Dual Super-Resolution Learning for Semantic Segmentation.
CVPR
Li Wang, Dong Li, Yousong Zhu, Lu Tian, Yi Shan
2020 — conf
MTNAS: Search Multi-task Networks for Autonomous Driving.
ACCV (3)
Hao Liu, Dong Li, Jinzhang Peng, Qingjie Zhao, Lu Tian, Yi Shan
2020 — conf
ProgressFace: Scale-Aware Progressive Learning for Face Detection.
ECCV (6)
Jiashu Zhu, Dong Li, Tiantian Han, Lu Tian, Yi Shan
2020 J jnl
Progressive Representation Adaptation for Weakly Supervised Object Localization.
IEEE Trans. Pattern Anal. Mach. Intell.
Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, Ming-Hsuan Yang
2017 J jnl
Learning Structured Semantic Embeddings for Visual Recognition.
CoRR
Dong Li, Hsin-Ying Lee, Jia-Bin Huang, Shengjin Wang, Ming-Hsuan Yang
2017 J jnl
Progressive Representation Adaptation for Weakly Supervised Object Localization.
CoRR
Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, Ming-Hsuan Yang
2016 — conf
Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints.
ECCV (4)
Dong Li, Wei-Chih Hung, Jia-Bin Huang, Shengjin Wang, Narendra Ahuja, Ming-Hsuan Yang
2016 A* conf
Weakly Supervised Object Localization with Progressive Domain Adaptation.
CVPR
Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, Ming-Hsuan Yang
2015 J jnl
Discriminative Middle-Level Parts Mining for Object Detection.
IEICE Trans. Inf. Syst.
Dong Li, Yali Li, Shengjin Wang
2015 B conf
Selective parts for fine-grained recognition.
ICIP
Dong Li, Yali Li, Shengjin Wang