Li Shen 0008 - researchr alias

researchr

You are not signed in
Sign in
Sign up

Viewing Publication 1 - 85 from 85

2025

On Efficient Training of Large-Scale Deep Learning ModelsLi Shen 0008, Yan Sun, Zhiyuan Yu, Liang Ding 0006, Xinmei Tian 0001, Dacheng Tao. ACM Comput. Surv., 57(3), March 2025. [doi]

Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution GeneralizationZhuo Huang, Muyang Li, Li Shen 0008, Jun Yu 0001, Chen Gong 0002, Bo Han 0003, Tongliang Liu. ijcv, 133(1):456-474, January 2025. [doi]

DFedGFM: Pursuing global consistency for Decentralized Federated Learning via global flatness and global momentumQinglun Li, Miao Zhang, Tao Sun 0005, Quanjun Yin, Li Shen 0008. NN, 184:107084, 2025. [doi]

Code-switching finetuning: Bridging multilingual pretrained language models for enhanced cross-lingual performanceChangtong Zan, Liang Ding 0006, Li Shen 0008, Yu Cao, Weifeng Liu 0001. eaai, 139:109532, 2025. [doi]

2024

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement LearningTianfu Wang 0002, Li Shen 0008, Qilin Fan, Tong Xu 0001, Tongliang Liu, Hui Xiong 0001. tsc, 17(3):1001-1015, May - June 2024. [doi]

A Unified Analysis of AdaGrad With Weighted Aggregation and Momentum AccelerationLi Shen 0008, Congliang Chen, Fangyu Zou, Zequn Jie, Ju Sun, Wei Liu 0005. tnn, 35(10):14482-14490, October 2024. [doi]

Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?Fei Wang 0032, Liang Ding 0006, Jun Rao, Ye Liu, Li Shen 0008, Changxing Ding. tomccap, 20(12), December 2024. [doi]

Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM PruningAbhinav Bandari, Lu Yin 0006, Cheng-Yu Hsieh, Ajay Jaiswal, Tianlong Chen, Li Shen 0008, Ranjay Krishna, Shiwei Liu 0003. emnlp 2024: 18089-18099 [doi]

Quantum Imitation LearningZhihao Cheng, Kaining Zhang, Li Shen 0008, Dacheng Tao. tnn, 35(10):14190-14204, October 2024. [doi]

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?Yang Dai, Oubo Ma, Longfei Zhang, Xingxing Liang, Shengchao Hu, Mengzhu Wang, Shouling Ji, Jincai Huang 0001, Li Shen 0008. nips 2024: [doi]

FedGAMMA: Federated Learning With Global Sharpness-Aware MinimizationRong Dai, Xun Yang 0001, Yan Sun, Li Shen 0008, Xinmei Tian 0001, Meng Wang 0001, Yongdong Zhang 0001. tnn, 35(12):17479-17492, December 2024. [doi]

Retain and Adapt: Online Sequential EEG Classification With Subject ShiftTiehang Duan, Zhenyi Wang, Li Shen 0008, Gianfranco Doretto, Donald A. Adjeroh, Fang Li, Cui Tao. tai, 5(9):4479-4492, September 2024. [doi]

Neural-aware Decoupling Fusion based Personalized Federated Learning for Intelligent SensingYujia Gao, Li Shen 0008, Liang Liu 0001, Zijian Cao 0002, Dacheng Tao, Huadong Ma, Nei Kato. tosn, 20(6), November 2024. [doi]

PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic SegmentationZhiwei Hao, Zhongyu Xiao, Yong Luo 0002, Jianyuan Guo, Jing Wang 0055, Li Shen 0008, Han Hu 0003. mm 2024: 1943-1951 [doi]

Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable LearningZiming Hong, Li Shen 0008, Tongliang Liu. cvpr 2024: 28805-28815 [doi]

Improving Non-Transferable Representation Learning by Harnessing Content and StyleZiming Hong, Zhenyi Wang, Li Shen 0008, Yu Yao, Zhuo Huang, Shiming Chen 0002, Chuanwu Yang, Mingming Gong, Tongliang Liu. iclr 2024: [doi]

Learning Multi-Agent Communication from Graph Modeling PerspectiveShengchao Hu, Li Shen 0008, Ya Zhang 0002, Dacheng Tao. iclr 2024: [doi]

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free ApplicationsZixuan Hu, Yongxian Wei, Li Shen 0008, Zhenyi Wang, Lei Li, Chun Yuan, Dacheng Tao. icml 2024: [doi]

HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement LearningShengchao Hu, Ziqing Fan, Li Shen 0008, Ya Zhang 0002, Yanfeng Wang, Dacheng Tao. icml 2024: [doi]

Q-value Regularized Transformer for Offline Reinforcement LearningShengchao Hu, Ziqing Fan, Chaoqin Huang, Li Shen 0008, Ya Zhang 0002, Yanfeng Wang, Dacheng Tao. icml 2024: [doi]

On Transforming Reinforcement Learning With Transformers: The Development TrajectoryShengchao Hu, Li Shen 0008, Ya Zhang 0002, Yixin Chen 0001, Dacheng Tao. pami, 46(12):8580-8599, December 2024. [doi]

Master-Slave Deep Architecture for Top-K Multiarmed Bandits With Nonlinear Bandit Feedback and Diversity ConstraintsHanchi Huang, Li Shen 0008, Deheng Ye, Wei Liu 0005. tnn, 35(12):17608-17619, December 2024. [doi]

Visual Prompt Based Personalized Federated LearningGuanghao Li, Wansen Wu, Yan Sun, Li Shen 0008, Baoyuan Wu, Dacheng Tao. tmlr, 2024, 2024. [doi]

MuEP: A Multimodal Benchmark for Embodied Planning with Foundation ModelsKanxue Li, Baosheng Yu, Qi Zheng, Yibing Zhan, Yuhui Zhang, Tianle Zhang, Yijun Yang, Yue Chen, Lei Sun, Qiong Cao, Li Shen 0008, Lusong Li, Dapeng Tao, Xiaodong He 0001. IJCAI 2024: 129-138 [doi]

Local AdaGrad-type algorithm for stochastic convex-concave optimizationLuofeng Liao, Li Shen 0008, Jia Duan, Mladen Kolar, Dacheng Tao. ml, 113(4):1819-1838, April 2024. [doi]

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal OptimizerBoan Liu, Liang Ding 0006, Li Shen 0008, Keqin Peng, Yu Cao, Dazhao Cheng, Dacheng Tao. ecai 2024: 2966-2973 [doi]

Decentralized Directed Collaboration for Personalized Federated LearningYingqi Liu, Yifan Shi, Baoyuan Wu, Qinglun Li, Xueqian Wang 0001, Li Shen 0008. cvpr 2024: 23168-23178 [doi]

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training StagesGuozheng Ma, Lu Li, Sen Zhang 0006, Zixuan Liu, Zhen Wang 0030, Yixin Chen 0001, Li Shen 0008, Xueqian Wang 0001, Dacheng Tao. iclr 2024: [doi]

Efficient Federated Learning With Enhanced Privacy via Lottery Ticket Pruning in Edge ComputingYifan Shi, Kang Wei, Li Shen 0008, Jun Li, Xueqian Wang 0001, Bo Yuan 0003, Song Guo 0001. tmc, 23(10):9946-9958, October 2024. [doi]

Multi-Scenario and Multi-Task Aware Feature Interaction for Recommendation SystemDerun Song, Enneng Yang, Guibing Guo, Li Shen 0008, Linying Jiang, Xingwei Wang 0001. tkdd, 18(6), July 2024. [doi]

AdaSAM: Boosting sharpness-aware minimization with adaptive learning rate and momentum for training deep neural networksHao Sun, Li Shen 0008, Qihuang Zhong, Liang Ding 0006, Shixiang Chen, Jingwei Sun 0001, Jing Li 0047, Guangzhong Sun, Dacheng Tao. NN, 169:506-519, January 2024. [doi]

Parameter-Efficient Multi-Task Model Fusion with Partial LinearizationAnke Tang, Li Shen 0008, Yong Luo 0002, Yibing Zhan, Han Hu 0003, Bo Du 0001, Yixin Chen 0001, Dacheng Tao. iclr 2024: [doi]

Merging Multi-Task Models via Weight-Ensembling Mixture of ExpertsAnke Tang, Li Shen 0008, Yong Luo 0002, Nan Yin, Lefei Zhang, Dacheng Tao. icml 2024: [doi]

WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World KnowledgeWenbin Wang, Liang Ding 0006, Li Shen 0008, Yong Luo 0002, Han Hu 0003, Dacheng Tao. mm 2024: 2282-2291 [doi]

Training A Secure Model Against Data-Free Model ExtractionZhenyi Wang, Li Shen 0008, Junfeng Guo, Tiehang Duan, Siyu Luan, Tongliang Liu, Mingchen Gao. eccv 2025: 323-340 [doi]

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language ModelsShuai Wang, Liang Ding 0006, Li Shen 0008, Yong Luo 0008, Bo Du 0001, Dacheng Tao. acl 2014: 13619-13639 [doi]

A Unified and General Framework for Continual LearningZhenyi Wang, Yan Li, Li Shen 0008, Heng Huang. iclr 2024: [doi]

Generalization Analysis of Stochastic Weight Averaging with General SamplingPeng Wang, Li Shen 0008, Zerui Tao, Shuaida He, Dacheng Tao. icml 2024: [doi]

Free: Faster and Better Data-Free Meta-LearningYongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen 0008, Chun Yuan, Dacheng Tao. cvpr 2024: 23273-23282 [doi]

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained ModelsYongxian Wei, Zixuan Hu, Li Shen 0008, Zhenyi Wang, Yu Li, Chun Yuan, Dacheng Tao. icml 2024: [doi]

Meta-Learning Without Data via Unconditional Diffusion ModelsYongxian Wei, Zixuan Hu, Li Shen 0008, Zhenyi Wang, Lei Li, Yu Li, Chun Yuan. tcsv, 34(11):11874-11885, November 2024. [doi]

AdaMerging: Adaptive Model Merging for Multi-Task LearningEnneng Yang, Zhenyi Wang, Li Shen 0008, Shiwei Liu 0003, Guibing Guo, Xingwei Wang 0001, Dacheng Tao. iclr 2024: [doi]

Representation Surgery for Multi-Task Model MergingEnneng Yang, Li Shen 0008, Zhenyi Wang, Guibing Guo, Xiaojun Chen 0006, Xingwei Wang 0001, Dacheng Tao. icml 2024: [doi]

Generalized Embedding Machines for Recommender SystemsEnneng Yang, Xin Xin 0007, Li Shen 0008, Yudong Luo, Guibing Guo. ijautcomp, 21(3):571-584, June 2024. [doi]

Continual Learning From a Stream of APIsEnneng Yang, Zhenyi Wang, Li Shen 0008, Nan Yin, Tongliang Liu, Guibing Guo, Xingwei Wang 0001, Dacheng Tao. pami, 46(12):11432-11445, December 2024. [doi]

SPORT: A Subgraph Perspective on Graph Classification with Label NoiseNan Yin, Li Shen 0008, Chong Chen 0002, Xiansheng Hua 0001, Xiao Luo 0001. tkdd, 18(9), November 2024. [doi]

Messages are Never Propagated Alone: Collaborative Hypergraph Neural Network for Time-Series ForecastingNan Yin, Li Shen 0008, Huan Xiong, Bin Gu 0001, Chong Chen 0002, Xian-Sheng Hua 0001, Siwei Liu 0001, Xiao Luo 0001. pami, 46(4):2333-2347, April 2024. [doi]

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain AdaptionNan Yin, Mengzhu Wang, Zhenghan Chen, Li Shen 0008, Huan Xiong, Bin Gu 0001, Xiao Luo 0001. iclr 2024: [doi]

Sheared Backpropagation for Fine-Tuning Foundation ModelsZhiyuan Yu, Li Shen 0008, Liang Ding 0006, Xinmei Tian 0001, Yixin Chen 0001, Dacheng Tao. cvpr 2024: 5883-5892 [doi]

Revisiting Knowledge Distillation for Autoregressive Language ModelsQihuang Zhong, Liang Ding 0006, Li Shen 0008, Juhua Liu, Bo Du 0001, Dacheng Tao. acl 2024: 10900-10913 [doi]

2023

Efficient-Adam: Communication-Efficient Distributed AdamCongliang Chen, Li Shen 0008, Wei Liu 0005, Zhi-Quan Luo. tsp, 71:3257-3266, 2023. [doi]

Off-policy Imitation Learning from Visual InputsZhihao Cheng, Li Shen 0008, Dacheng Tao. icra 2023: 2937-2943 [doi]

Offline Quantum Reinforcement Learning in a Conservative MannerZhihao Cheng, Kaining Zhang, Li Shen 0008, Dacheng Tao. AAAI 2023: 7148-7156 [doi]

Prescribed Safety Performance Imitation Learning From a Single Expert DatasetZhihao Cheng, Li Shen 0008, Miaoxi Zhu, Jiaxian Guo, Meng Fang, Liu Liu 0014, Bo Du 0001, Dacheng Tao. pami, 45(10):12236-12249, October 2023. [doi]

FedDAG: Federated DAG Structure LearningErdun Gao, Junjia Chen, Li Shen 0008, Tongliang Liu, Mingming Gong, Howard D. Bondell. tmlr, 2023, 2023. [doi]

Task-Adaptive Feature Disentanglement and Hallucination for Few-Shot ClassificationZixuan Hu, Li Shen 0008, Shenqi Lai, Chun Yuan. tcsv, 33(8):3638-3648, August 2023. [doi]

Fusion of Global and Local Knowledge for Personalized Federated LearningTiansheng Huang, Li Shen 0008, Yan Sun, Weiwei Lin 0001, Dacheng Tao. tmlr, 2023, 2023. [doi]

Curriculum-Based Asymmetric Multi-Task Reinforcement LearningHanchi Huang, Deheng Ye, Li Shen 0008, Wei Liu 0005. pami, 45(6):7258-7269, June 2023. [doi]

Differentiable Neural Architecture Search for Extremely Lightweight Image Super-ResolutionHan Huang, Li Shen 0008, Chaoyang He 0001, Weisheng Dong, Wei Liu 0005. tcsv, 33(6):2672-2682, June 2023. [doi]

FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised LearningZhuo Huang, Li Shen 0008, Jun Yu, Bo Han 0003, Tongliang Liu. nips 2023: [doi]

Harnessing Out-Of-Distribution Examples via Augmenting Content and StyleZhuo Huang, Xiaobo Xia, Li Shen 0008, Bo Han 0003, Mingming Gong, Chen Gong 0002, Tongliang Liu. iclr 2023: [doi]

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness MinimizationZhuo Huang, Miaoxi Zhu, Xiaobo Xia, Li Shen 0008, Jun Yu 0001, Chen Gong 0002, Bo Han 0003, Bo Du 0001, Tongliang Liu. cvpr 2023: 16175-16185 [doi]

Enhancing Adversarial Training via Reweighting Optimization TrajectoryTianjin Huang, Shiwei Liu, Tianlong Chen, Meng Fang, Li Shen 0008, Vlado Menkovski, Lu Yin 0006, Yulong Pei, Mykola Pechenizkiy. pkdd 2023: 113-130 [doi]

Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing PerformanceShiwei Liu, Yuesong Tian, Tianlong Chen, Li Shen 0008. ijcv, 131(10):2635-2648, October 2023. [doi]

Towards Stable Backdoor Purification through Feature Shift TuningRui Min, Zeyu Qin, Li Shen 0008, Minhao Cheng. nips 2023: [doi]

Dynamic Contrastive Distillation for Image-Text RetrievalJun Rao, Liang Ding 0006, Shuhan Qi, Meng Fang, Yang Liu 0039, Li Shen 0008, Dacheng Tao. tmm, 25:8383-8395, 2023. [doi]

Improving the Model Consistency of Decentralized Federated LearningYifan Shi, Li Shen 0008, Kang Wei, Yan Sun, Bo Yuan 0003, Xueqian Wang 0001, Dacheng Tao. icml 2023: 31269-31291 [doi]

FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization AccuracyYan Sun, Li Shen 0008, Tiansheng Huang, Liang Ding 0006, Dacheng Tao. iclr 2023: [doi]

Efficient Federated Learning Via Local Adaptive Amended Optimizer With Linear SpeedupYan Sun, Li Shen 0008, Hao Sun, Liang Ding 0006, Dacheng Tao. pami, 45(12):14453-14464, December 2023. [doi]

Dynamic PDGAN: discriminator-boosted knowledge distillation for StyleGANsYuesong Tian, Li Shen 0008, Xiang Tian, Zhifeng Li, Yaowu Chen. jei, 33(1), 2023. [doi]

Distributionally Robust Memory Evolution With Generalized Divergence for Continual LearningZhenyi Wang, Li Shen 0008, Tiehang Duan, Qiuling Suo, Le Fang, Wei Liu 0005, Mingchen Gao. pami, 45(12):14337-14352, December 2023. [doi]

OMG: Towards Effective Graph Classification Against Label NoiseNan Yin, Li Shen 0008, Mengzhu Wang, Xiao Luo 0001, Zhigang Luo, Dacheng Tao. tkde, 35(12):12873-12886, December 2023. [doi]

Learning Meta Representations for Agents in Multi-Agent Reinforcement LearningShenao Zhang, Li Shen 0005, Lei Han, Li Shen 0008. collas 2023: 292-317 [doi]

Evaluating Model-Free Reinforcement Learning toward Safety-Critical TasksLinrui Zhang, Qin Zhang, Li Shen 0008, Bo Yuan 0003, Xueqian Wang 0001, Dacheng Tao. AAAI 2023: 15313-15321 [doi]

Enhancing Fine-Tuning based Backdoor Defense with Sharpness-Aware MinimizationMingli Zhu, Shaokui Wei, Li Shen 0008, Yanbo Fan, Baoyuan Wu. iccv 2023: 4443-4454 [doi]

Zero-shot Sharpness-Aware Quantization for Pre-trained Language ModelsMiaoxi Zhu, Qihuang Zhong, Li Shen 0008, Liang Ding 0006, Juhua Liu, Bo Du 0001, Dacheng Tao. emnlp 2023: 11305-11327 [doi]

2022

DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse TrainingRong Dai, Li Shen 0008, Fengxiang He, Xinmei Tian 0001, Dacheng Tao. icml 2022: 4587-4604 [doi]

Stochastic Client Selection for Federated Learning With Volatile ClientsTiansheng Huang, Weiwei Lin, Li Shen 0008, Keqin Li 0001, Albert Y. Zomaya. iotj, 9(20):20055-20070, 2022. [doi]

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse TrainingShiwei Liu, Tianlong Chen, Xiaohan Chen, Li Shen 0008, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy. iclr 2022: [doi]

Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation ApproachPeng Mi, Li Shen 0008, Tianhe Ren, Yiyi Zhou, Xiaoshuai Sun, Rongrong Ji, Dacheng Tao. nips 2022: [doi]

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial PerturbationZeyu Qin, Yanbo Fan, Yi Liu, Li Shen 0008, Yong Zhang, Jue Wang 0001, Baoyuan Wu. nips 2022: [doi]

AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial NetworksYuesong Tian, Li Shen 0008, Li Shen 0005, Guinan Su, Zhifeng Li 0001, Wei Liu 0005. pami, 44(10):6752-6766, 2022. [doi]

On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine TranslationChangtong Zan, Liang Ding 0006, Li Shen 0008, Yu Cao, Weifeng Liu 0001, Dacheng Tao. COLING 2022: 5029-5034 [doi]

Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language ModelsQihuang Zhong, Liang Ding 0006, Li Shen 0008, Peng Mi, Juhua Liu, Bo Du 0001, Dacheng Tao. emnlp 2022: 4064-4085 [doi]

2021

Sparse Training via Boosting Pruning Plasticity with NeuroregenerationShiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin 0006, Huanyu Kou, Li Shen 0008, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu. nips 2021: 9908-9922 [doi]

See Also

All Publications

Filter by Year
OR AND NOT 1

Filter by Type
OR AND NOT 1

Filter by Tag

Filter by Venue

[+]
OR AND NOT 1

Filter by Author

[+]
OR AND NOT 1

Filter by Top Terms

[+]
OR AND NOT 1

Researchr

Publications by 'Li Shen 0008'

Viewing Publication 1 - 85 from 85

2025

2024

2023

2022

2021

See Also

All Publications

Filter by YearOR AND NOT 1

Filter by TypeOR AND NOT 1

Filter by Tag

Filter by Venue [+]OR AND NOT 1

Filter by Author [+]OR AND NOT 1

Filter by Top Terms [+]OR AND NOT 1

Researchr

Publications by 'Li Shen 0008'

Viewing Publication 1 - 85 from 85

2025

2024

2023

2022

2021

Filter by Year
OR AND NOT 1

Filter by Type
OR AND NOT 1

Filter by Venue

[+]
OR AND NOT 1

Filter by Author

[+]
OR AND NOT 1

Filter by Top Terms

[+]
OR AND NOT 1