Shengen Yan

72 papers A* 11A 3B 10Misc 1Journal 39Unranked 8
YearRankTypeTitle / Venue / Authors
2026 A conf
STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal Planning.
EuroSys
Zixiao Huang, Junhao Hu, Hao Lin, Chunyang Zhu, Yueran Tang, Quanlu Zhang, Zhen Guo, Zhenhua Li, Shengen Yan, Zhenhua Zhu, Guohao Dai, Yu Wang
2025 — conf
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms.
WWW (Companion Volume)
Yuwei Yan, Yu Shang, Qingbin Zeng, Yu Li, Keyu Zhao, Zhiheng Zheng, Xuefei Ning, Tianji Wu, Shengen Yan, Yu Wang, Fengli Xu, Yong Li
2025 J jnl
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms.
CoRR
Yuwei Yan, Yu Shang, Qingbin Zeng, Yu Li, Keyu Zhao, Zhiheng Zheng, Xuefei Ning, Tianji Wu, Shengen Yan, Yu Wang, Fengli Xu, Yong Li
2025 J jnl
BitSnap: Checkpoint Sparsification and Quantization in LLM Training.
CoRR
Yanxin Peng, Qingping Li, Baodong Wu, Shigang Li, Guohao Dai, Shengen Yan, Yu Wang
2025 A* conf
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation.
ACM Multimedia
Zhihang Yuan, Siyuan Wang, Yuzhang Shang, Hanling Zhang, Tongcheng Fang, Rui Xie, Shengen Yan, Guohao Dai, Yu Wang
2025 J jnl
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation.
CoRR
Zhihang Yuan, Siyuan Wang, Rui Xie, Hanling Zhang, Tongcheng Fang, Yuzhang Shang, Shengen Yan, Guohao Dai, Yu Wang
2025 J jnl
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers.
CoRR
Hanling Zhang, Rundong Su, Zhihang Yuan, Pengtao Chen, Mingzhu Shen, Yibo Fan, Shengen Yan, Guohao Dai, Yu Wang
2025 J jnl
Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation.
CoRR
Enshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai, Zinan Lin, Yu Wang
2025 J jnl
FlashDecoding++Next: High Throughput LLM Inference With Latency and Memory Optimization.
IEEE Trans. Computers
Guohao Dai, Ke Hong, Qiuli Mao, Xiuhong Li, Jiaming Xu, Haofeng Huang, Hongtu Xia, Xuefei Ning, Shengen Yan, Yun Liang, Yu Wang
2025 J jnl
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models.
CoRR
Tianyu Fu, Tengxuan Liu, Qinghao Han, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
2025 A* conf
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better.
ICLR
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
2025 A* conf
MBQ: Modality-Balanced Quantization for Large Vision-Language Models.
CVPR
Shiyao Li, Yingchun Hu, Xuefei Ning, Xihui Liu, Ke Hong, Xiaotao Jia, Xiuhong Li, Yaqi Yan, Pei Ran, Guohao Dai, Shengen Yan, Huazhong Yang, Yu Wang
2025 J jnl
Megrez-Omni Technical Report.
CoRR
Boxun Li, Yadong Li, Zhiyuan Li, Congyi Liu, Weilin Liu, Guowei Niu, Zheyue Tan, Haiyang Xu, Zhuyu Yao, Tao Yuan, Dong Zhou, Yueqing Zhuang, Shengen Yan, Guohao Dai, Yu Wang
2025 J jnl
PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs.
CoRR
Tengxuan Liu, Shiyao Li, Jiayi Yang, Tianchen Zhao, Feng Zhou, Xiaohui Song, Guohao Dai, Shengen Yan, Huazhong Yang, Yu Wang
2025 J jnl
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing.
CoRR
Tianyu Fu, Yi Ge, Yichen You, Enshu Liu, Zhihang Yuan, Guohao Dai, Shengen Yan, Huazhong Yang, Yu Wang
2025 J jnl
Reducing GPU Memory Fragmentation via Spatio-Temporal Planning for Efficient Large-Scale Model Training.
CoRR
Zixiao Huang, Junhao Hu, Hao Lin, Chunyang Zhu, Yueran Tang, Quanlu Zhang, Zhen Guo, Zhenhua Li, Shengen Yan, Zhenhua Zhu, Guohao Dai, Yu Wang
2025 — conf
SOLA: Optimizing SLO Attainment for Large Language Model Serving with State-Aware Scheduling.
MLSys
Ke Hong, Xiuhong Li, Lufang Chen, Qiuli Mao, Guohao Dai, Xuefei Ning, Shengen Yan, Yun Liang, Yu Wang
2025 J jnl
VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate.
CoRR
Zhihang Yuan, Rui Xie, Yuzhang Shang, Hanling Zhang, Siyuan Wang, Shengen Yan, Guohao Dai, Yu Wang
2025 A* conf
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation.
ICLR
Tianchen Zhao, Tongcheng Fang, Haofeng Huang, Rui Wan, Widyadewi Soedarmadji, Enshu Liu, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
2024 A* conf
A Holistic Functionalization Approach to Optimizing Imperative Tensor Programs in Deep Learning.
DAC
Jinming Ma, Xiuhong Li, Zihan Wang, Xingcheng Zhang, Shengen Yan, Yuting Chen, Yueqian Zhang, Minxi Jin, Lijuan Jiang, Yun Liang, Chao Yang, Dahua Lin
2024 J jnl
A Survey on Efficient Inference for Large Language Models.
CoRR
Zixuan Zhou, Xuefei Ning, Ke Hong, Tianyu Fu, Jiaming Xu, Shiyao Li, Yuming Lou, Luning Wang, Zhihang Yuan, Xiuhong Li, Shengen Yan, Guohao Dai, Xiao-Ping Zhang, Yuhan Dong, Yu Wang
2024 A* conf
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction.
NeurIPS
Renze Chen, Zhuofeng Wang, Beiquan Cao, Tong Wu, Size Zheng, Xiuhong Li, Xuechao Wei, Shengen Yan, Meng Li, Yun Liang
2024 — conf
CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios.
ENLSP
Luning Wang, Shiyao Li, Xuefei Ning, Zhihang Yuan, Shengen Yan, Guohao Dai, Yu Wang
2024 J jnl
CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios.
CoRR
Luning Wang, Shiyao Li, Xuefei Ning, Zhihang Yuan, Shengen Yan, Guohao Dai, Yu Wang
2024 A* conf
DiTFastAttn: Attention Compression for Diffusion Transformer Models.
NeurIPS
Zhihang Yuan, Hanling Zhang, Lu Pu, Xuefei Ning, Linfeng Zhang, Tianchen Zhao, Shengen Yan, Guohao Dai, Yu Wang
2024 J jnl
DiTFastAttn: Attention Compression for Diffusion Transformer Models.
CoRR
Zhihang Yuan, Pu Lu, Hanling Zhang, Xuefei Ning, Linfeng Zhang, Tianchen Zhao, Shengen Yan, Guohao Dai, Yu Wang
2024 J jnl
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling.
CoRR
Zhihang Yuan, Yuzhang Shang, Hanling Zhang, Tongcheng Fang, Rui Xie, Bingxin Xu, Yan Yan, Shengen Yan, Guohao Dai, Yu Wang
2024 J jnl
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs.
CoRR
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
2024 A* conf
Evaluating Quantized Large Language Models.
ICML
Shiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu, Xiangsheng Shi, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
2024 J jnl
Evaluating Quantized Large Language Models.
CoRR
Shiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu, Xiangsheng Shi, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
2024 J jnl
HetHub: A Heterogeneous distributed hybrid training system for large-scale models.
CoRR
Si Xu, Zixiao Huang, Yan Zeng, Shengen Yan, Xuefei Ning, Haolin Ye, Sipei Gu, Chunsheng Shui, Zhezheng Lin, Hao Zhang, Sheng Wang, Guohao Dai, Yu Wang
2024 J jnl
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K.
CoRR
Tao Yuan, Xuefei Ning, Dong Zhou, Zhijie Yang, Shiyao Li, Minghui Zhuang, Zheyue Tan, Zhuyu Yao, Dahua Lin, Boxun Li, Guohao Dai, Shengen Yan, Yu Wang
2024 J jnl
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better.
CoRR
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
2024 J jnl
MBQ: Modality-Balanced Quantization for Large Vision-Language Models.
CoRR
Shiyao Li, Yingchun Hu, Xuefei Ning, Xihui Liu, Ke Hong, Xiaotao Jia, Xiuhong Li, Yaqi Yan, Pei Ran, Guohao Dai, Shengen Yan, Huazhong Yang, Yu Wang
2024 — conf
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization.
ECCV (14)
Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
2024 J jnl
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization.
CoRR
Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
2024 J jnl
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression.
CoRR
Tianyu Fu, Haofeng Huang, Xuefei Ning, Genghan Zhang, Boju Chen, Tianqi Wu, Hongyi Wang, Zixiao Huang, Shiyao Li, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
2024 J jnl
Proteus: Simulating the Performance of Distributed DNN Training.
IEEE Trans. Parallel Distributed Syst.
Jiangfei Duan, Xiuhong Li, Ping Xu, Xingcheng Zhang, Shengen Yan, Yun Liang, Dahua Lin
2024 J jnl
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation.
CoRR
Tianchen Zhao, Tongcheng Fang, Enshu Liu, Rui Wan, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
2023 A* conf
Chimera: An Analytical Optimizing Framework for Effective Compute-intensive Operators Fusion.
HPCA
Size Zheng, Siyuan Chen, Peidi Song, Renze Chen, Xiuhong Li, Shengen Yan, Dahua Lin, Jingwen Leng, Yun Liang
2023 J jnl
Proteus: Simulating the Performance of Distributed DNN Training.
CoRR
Jiangfei Duan, Xiuhong Li, Ping Xu, Xingcheng Zhang, Shengen Yan, Yun Liang, Dahua Lin
2022 J jnl
A Simulation Platform for Multi-tenant Machine Learning Services on Thousands of GPUs.
CoRR
Ruofan Liang, Bingsheng He, Shengen Yan, Peng Sun
2022 A* conf
AMOS: enabling automatic mapping for tensor computations on spatial accelerators with hardware abstraction.
ISCA
Size Zheng, Renze Chen, Anjiang Wei, Yicheng Jin, Qin Han, Liqiang Lu, Bingyang Wu, Xiuhong Li, Shengen Yan, Yun Liang
2022 J jnl
Astraea: A Fair Deep Learning Scheduler for Multi-Tenant GPU Clusters.
IEEE Trans. Parallel Distributed Syst.
Zhisheng Ye, Peng Sun, Wei Gao, Tianwei Zhang, Xiaolin Wang, Shengen Yan, Yingwei Luo
2022 J jnl
DIESEL+: Accelerating Distributed Deep Learning Tasks on Image Datasets.
IEEE Trans. Parallel Distributed Syst.
Lipeng Wang, Qiong Luo, Shengen Yan
2022 B conf
EasyView: Enabling and Scheduling Tensor Views in Deep Learning Compilers.
ICPP
Lijuan Jiang, Ping Xu, Qianchao Zhu, Xiuhong Li, Shengen Yan, Xingcheng Zhang, Dahua Lin, Wenjing Ma, Zhouyang Li, Jun Liu, Jinming Ma, Minxi Jin, Chao Yang
2022 J jnl
GradientFlow: Optimizing Network Performance for Large-Scale Distributed DNN Training.
IEEE Trans. Big Data
Peng Sun, Yonggang Wen, Ruobing Han, Wansen Feng, Shengen Yan
2022 — conf
LongTail-Bench: A Benchmark Suite for Domain-Specific Operators in Deep Learning.
IISWC
Xiuhong Li, Shengen Yan, Lijuan Jiang, Ping Xu, Jinming Ma, Xingcheng Zhang, Dahua Lin
2022 J jnl
NeoFlow: A Flexible Framework for Enabling Efficient Compilation for High Performance DNN Training.
IEEE Trans. Parallel Distributed Syst.
Size Zheng, Renze Chen, Yicheng Jin, Anjiang Wei, Bingyang Wu, Xiuhong Li, Shengen Yan, Yun Liang
2021 J jnl
Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters.
CoRR
Qinghao Hu, Peng Sun, Shengen Yan, Yonggang Wen, Tianwei Zhang
2021 A conf
Characterization and prediction of deep learning workloads in large-scale GPU datacenters.
SC
Qinghao Hu, Peng Sun, Shengen Yan, Yonggang Wen, Tianwei Zhang
2020 B conf
Accelerating Deep Learning Tasks with Optimized GPU-assisted Image Decoding.
ICPADS
Lipeng Wang, Qiong Luo, Shengen Yan
2020 B conf
DIESEL: A Dataset-Based Distributed Storage and Caching System for Large-Scale Deep Learning Training.
ICPP
Lipeng Wang, Songgao Ye, Baichen Yang, Youyou Lu, Hequan Zhang, Shengen Yan, Qiong Luo
2020 A conf
Elan: Towards Generic and Efficient Elastic Training for Deep Learning.
ICDCS
Lei Xie, Jidong Zhai, Baodong Wu, Yuanbo Wang, Xingcheng Zhang, Peng Sun, Shengen Yan
2020 J jnl
Enabling Efficient Fast Convolution Algorithms on GPUs via MegaKernels.
IEEE Trans. Computers
Liancheng Jia, Yun Liang, Xiuhong Li, Liqiang Lu, Shengen Yan
2020 J jnl
Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Yun Liang, Liqiang Lu, Qingcheng Xiao, Shengen Yan
2019 B conf
A coordinated tiling and batching framework for efficient GEMM on GPUs.
PPoPP
Xiuhong Li, Yun Liang, Shengen Yan, Liancheng Jia, Yinghan Li
2019 J jnl
Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes.
CoRR
Peng Sun, Wansen Feng, Ruobing Han, Shengen Yan, Yonggang Wen
2019 J jnl
面向GPU计算平台的归约算法的性能优化研究 (Study on Performance Optimization of Reduction Algorithm Targeting GPU Computing Platform).
计算机科学
Yiran Zhang, Long Chen, Xiangzhe An, Shengen Yan
2017 Misc conf
Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs.
FCCM
Liqiang Lu, Yun Liang, Qingcheng Xiao, Shengen Yan
2017 A* conf
Exploring Heterogeneous Algorithms for Accelerating Deep Convolutional Neural Networks on FPGAs.
DAC
Qingcheng Xiao, Yun Liang, Liqiang Lu, Shengen Yan, Yu-Wing Tai
2017 B conf
Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach.
SMARTCOMP
Peng Sun, Yonggang Wen, Ta Nguyen Binh Duong, Shengen Yan
2017 J jnl
Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach.
CoRR
Peng Sun, Yonggang Wen, Ta Nguyen Binh Duong, Shengen Yan
2016 J jnl
A Cross-Platform SpMV Framework on Many-Core Architectures.
ACM Trans. Archit. Code Optim.
Yunquan Zhang, Shigang Li, Shengen Yan, Huiyang Zhou
2016 B conf
Timed Dataflow: Reducing Communication Overhead for Distributed Machine Learning Systems.
ICPADS
Peng Sun, Yonggang Wen, Ta Nguyen Binh Duong, Shengen Yan
2014 B conf
A fast integral image generation algorithm on GPUs.
ICPADS
Qingqing Dang, Shengen Yan, Ren Wu
2014 B conf
Understanding the tradeoffs between software-managed vs. hardware-managed caches in GPUs.
ISPASS
Chao Li, Yi Yang, Hongwen Dai, Shengen Yan, Frank Mueller, Huiyang Zhou
2014 B conf
yaSpMV: yet another SpMV framework on GPUs.
PPoPP
Shengen Yan, Chao Li, Yunquan Zhang, Huiyang Zhou
2013 — conf
CLSIFT: An Optimization Study of the Scale Invariance Feature Transform on GPUs.
HPCC/EUC
Weiyan Wang, Yunquan Zhang, Guoping Long, Shengen Yan, Haipeng Jia
2013 B conf
StreamScan: fast scan algorithms for GPUs without global barrier synchronization.
PPoPP
Shengen Yan, Guoping Long, Yunquan Zhang
2012 — conf
An Insightful Program Performance Tuning Chain for GPU Computing.
ICA3PP (1)
Haipeng Jia, Yunquan Zhang, Guoping Long, Shengen Yan
2012 — conf
GPURoofline: A Model for Guiding Performance Optimizations on GPUs.
Euro-Par
Haipeng Jia, Yunquan Zhang, Guoping Long, Jianliang Xu, Shengen Yan, Yan Li