Scaling LLM Test-Time Compute with Mobile NPU on Smartphones.

Ting Cao 0003 https://orcid.org/0000-0002-9107-013X https://www.wikidata.org/entity/Q130814152 Microsoft Research, Beijing, China Ting Cao Ting Cao 0001 https://orcid.org/0000-0003-2079-0225 Xi'an University of Technology, Xi'an, China Ting Cao 0002 https://orcid.org/0000-0001-5959-1106 Xi'an University of Technology, School of Computer Science and Engineering, China Ting Cao 0004 https://orcid.org/0000-0002-7675-0882 Xi'an University of Technology, Xi'an, Shaanxi, China Ting Cao 0005 https://orcid.org/0000-0001-8117-1941 Wuhan University, Wuhan, China Ting Cao 0006 https://orcid.org/0000-0002-9590-471X Peng Cheng Laboratory, Shenzhen, Guangdong, China Ting Cao 0007 https://orcid.org/0000-0002-8256-682X Microsoft Research Asia, Beijing, China Ting Cao 0008 https://orcid.org/0000-0003-1300-6084 https://www.wikidata.org/entity/Q59600682 University of Washington, Seattle, WA, USA Zixu Hao Jianyu Wei Tuowei Wang Minxing Huang Huiqiang Jiang Shiqi Jiang 0002 Ting Cao 0003 Ju Ren 0001 Scaling LLM Test-Time Compute with Mobile NPU on Smartphones. 2157-2172 2026 EuroSys https://doi.org/10.1145/3767295.3769382 conf/eurosys/2026 db/conf/eurosys/eurosys2026.html#HaoWWHJJCR26 Dayou Du Shijie Cao Jianyi Cheng Luo Mai Ting Cao 0003 Mao Yang 0004 BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache. HPCA 2026 1-13 conf/hpca/2026 https://doi.org/10.1109/HPCA68181.2026.11408481 db/conf/hpca/hpca2026.html#DuCCMCY26 streams/conf/hpca Xiangyu Li Chengyu Yin Weijun Wang 0001 Jianyu Wei Ting Cao 0003 Yunxin Liu 0001 Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices. 216-230 2026 MobiSys https://doi.org/10.1145/3745756.3809200 conf/mobisys/2026 db/conf/mobisys/mobisys2026.html#LiYWWCL26 Yuxuan Yan Shiqi Jiang 0002 Ting Cao 0003 Yifan Yang 0004 Qianqian Yang 0002 Yuanchao Shu Yuqing Yang 0001 Lili Qiu AVA: Towards Agentic Video Analytics with Vision Language Models. 1939-1957 2026 NSDI https://www.usenix.org/conference/nsdi26/presentation/yan conf/nsdi/2026 db/conf/nsdi/nsdi2026.html#YanJCYYSYQ26 Liang Mi Weijun Wang 0001 Jinghan Chen Ting Cao 0003 Haipeng Dai 0001 Yunxin Liu 0001 Efficient Remote KV Cache Reuse with GPU-native Video Codec. 30-45 2026 SIGCOMM https://doi.org/10.1145/3789240.3829120 conf/sigcomm/2026 db/conf/sigcomm/sigcomm2026.html#MiWCCDL26

Liang Mi Weijun Wang 0001 Jinghan Chen Ting Cao 0003 Haipeng Dai 0001 Yunxin Liu 0001 Efficient Remote Prefix Fetching with GPU-native Media ASICs. 2026 February abs/2602.09725 CoRR https://doi.org/10.48550/arXiv.2602.09725 db/journals/corr/corr2602.html#abs-2602-09725 streams/journals/corr

Yikai Zheng Xin Ding Yifan Yang 0004 Shiqi Jiang 0002 Hao Wu 0067 Qianxi Zhang Weijun Wang 0001 Ting Cao 0003 Yunxin Liu 0001 Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding. 2026 March abs/2603.19054 CoRR https://doi.org/10.48550/arXiv.2603.19054 db/journals/corr/corr2603.html#abs-2603-19054 streams/journals/corr

Haozhi Han Ruge Zhang Haoquan Chen Yifeng Chen Haipeng Jia Liang Yuan Yunquan Zhang Ting Cao 0003 Yunxin Liu 0001 Ya-Qin Zhang Kun Li 0016 Unfolding an Atomistic World: Atomistic Simulation of Reactor Pressure Vessel Steel Across Year-and-Meter Scales. 2026 April abs/2604.24091 CoRR https://doi.org/10.48550/arXiv.2604.24091 db/journals/corr/corr2604.html#abs-2604-24091 streams/journals/corr

Xin Ding Xinrui Wang Yifan Yang 0004 Hao Wu 0067 Shiqi Jiang 0002 Qianxi Zhang Liang Mi Hanxin Zhu Kun Li 0016 Yunxin Liu 0001 Zhibo Chen 0001 Ting Cao 0003 MemCompiler: Compile, Don't Inject - State-Conditioned Memory for Embodied Agents. 2026 May abs/2605.07594 CoRR https://doi.org/10.48550/arXiv.2605.07594 db/journals/corr/corr2605.html#abs-2605-07594 streams/journals/corr

Ruofei Ju Xinrui Wang Xin Ding Yifan Yang 0004 Hao Wu 0067 Shiqi Jiang 0002 Qianxi Zhang Hao Wen 0004 Xiangyu Li Weijun Wang 0001 Kun Li 0016 Yunxin Liu 0001 Haipeng Dai 0001 Wei Wang 0002 Ting Cao 0003 EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents. 2026 May abs/2605.10332 CoRR https://doi.org/10.48550/arXiv.2605.10332 db/journals/corr/corr2605.html#abs-2605-10332 streams/journals/corr

Mingzhe Huang Weijun Wang 0001 Xin Ding Liang Mi Hao Wen 0004 Yuanchun Li 0001 Lichen Pang Shansong Yang Yunxin Liu 0001 Ting Cao 0003 GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models. 2026 May abs/2605.13375 CoRR https://doi.org/10.48550/arXiv.2605.13375 db/journals/corr/corr2605.html#abs-2605-13375 streams/journals/corr

Bingjia Huang Xiangyu Li Xiang Wang Liang Mi Zixu Hao Weijun Wang 0001 Hao Wu 0067 Kun Li 0016 Yunxin Liu 0001 Ting Cao 0003 ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies. 2026 June abs/2606.08508 CoRR https://doi.org/10.48550/arXiv.2606.08508 db/journals/corr/corr2606.html#abs-2606-08508 streams/journals/corr

Tatsuya Kubo Daichi Tokuda Lei Qu Ting Cao 0003 Shinya Takamaeda-Yamazaki PUDTune: Multi-Level Charging for High-Precision Calibration in Processing-Using-DRAM. 245-248 2025 July - December 24 IEEE Comput. Archit. Lett. 2 https://doi.org/10.1109/LCA.2025.3585312 db/journals/cal/cal24.html#KuboTQCT25 streams/journals/cal

Qipeng Wang 0001 Shiqi Jiang 0002 Yifan Yang 0004 Ruiqi Liu 0001 Yuanchun Li 0003 Ting Cao 0003 Xuanzhe Liu Efficient and Adaptive Diffusion Model Inference Through Lookup Table on Mobile Devices. 8729-8746 2025 September 24 IEEE Trans. Mob. Comput. 9 https://doi.org/10.1109/TMC.2025.3558203 db/journals/tmc/tmc24.html#WangJYLLCL25 streams/journals/tmc

Jiaxu Qian Chendong Wang Yifan Yang 0004 Chaoyun Zhang Huiqiang Jiang Xufang Luo Yu Kang 0006 Qingwei Lin Anlan Zhang Shiqi Jiang 0002 Ting Cao 0003 Tianjun Mao Suman Banerjee 0001 Guyue Liu Saravan Rajmohan Dongmei Zhang 0001 Yuqing Yang 0001 Qi Zhang 0066 Lili Qiu Zoomer: Adaptive Image Focus Optimization for Black-box MLLM. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=u7RPDvumdF db/journals/tmlr/tmlr2025.html#QianWYZJLKLZJCMBLRZYZQ25 streams/journals/tmlr

Qipeng Wang 0001 Shiqi Jiang 0002 Zhenpeng Chen 0001 Xu Cao Yuanchun Li 0003 Aoyu Li Yun Ma 0002 Ting Cao 0003 Xuanzhe Liu Anatomizing Deep Learning Inference in Web Browsers. 47:1-47:43 2025 February 34 ACM Trans. Softw. Eng. Methodol. 2 https://doi.org/10.1145/3688843 https://www.wikidata.org/entity/Q130814155 db/journals/tosem/tosem34.html#WangJCCLLMCL25 streams/journals/tosem

Tuowei Wang Ruwen Fan Minxing Huang Zixu Hao Kun Li 0016 Ting Cao 0003 Youyou Lu Yaoxue Zhang Ju Ren 0001 Neuralink: Fast on-Device LLM Inference with Neuron Co-Activation Linking. 147-162 2025 ASPLOS (3) https://doi.org/10.1145/3676642.3736114 conf/asplos/2025-3 db/conf/asplos/asplos2025-3.html#WangFHH00LZ025 Jianyu Wei Shijie Cao Ting Cao 0003 Lingxiao Ma Lei Wang 0222 Yanyong Zhang Mao Yang 0004 T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge. 278-292 2025 EuroSys https://doi.org/10.1145/3689031.3696099 conf/eurosys/2025 db/conf/eurosys/eurosys2025.html#WeiCCMWZY25 Guoyu Li Shengyu Ye Chunyun Chen Yang Wang 0053 Fan Yang 0024 Ting Cao 0003 Cheng Liu 0008 Mohamed M. Sabry Aly Mao Yang 0004 LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator. 671-684 2025 HPCA https://doi.org/10.1109/HPCA61900.2025.00057 conf/hpca/2025 db/conf/hpca/hpca2025.html#LiYCWYCLA025 Xin Ding Hao Wu 0067 Yifan Yang 0004 Shiqi Jiang 0002 Qianxi Zhang Donglin Bai Zhibo Chen 0001 Ting Cao 0003 StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition. 2025 ICCV 13448-13459 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.01249 db/conf/iccv/iccv2025.html#DingWYJZBCC25 streams/conf/iccv Zhiwen Mo Lei Wang 0222 Jianyu Wei Zhichen Zeng 0002 Shijie Cao Lingxiao Ma Naifeng Jing Ting Cao 0003 Jilong Xue Fan Yang 0024 Mao Yang 0004 LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference. 514-528 2025 ISCA https://doi.org/10.1145/3695053.3731057 conf/isca/2025 db/conf/isca/isca2025.html#MoWW0CMJCX0025 Xin Ding Jianyu Wei Fucheng Jia Liang Mi Ruofei Ju Xianye Wang Yikai Zheng Ziming Zhang Weijun Wang 0001 Shiqi Jiang 0002 Yunxin Liu 0001 Ting Cao 0003 Demo: EdgeMind-OS: A Plug-and-Play Embodied Intelligence System for Real-Time On-Device Deployment. 1219-1221 2025 MobiCom https://doi.org/10.1145/3680207.3765596 conf/mobicom/2025 db/conf/mobicom/mobicom2025.html#DingWJMJWZZW00025 Yizhao Gao 0002 Zhichen Zeng 0002 Dayou Du Shijie Cao Peiyuan Zhou Jiaxing Qi Junjie Lai Hayden K. H. So Ting Cao 0003 Fan Yang 0024 Mao Yang 0004 SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling. 2025 NeurIPS http://papers.nips.cc/paper_files/paper/2025/hash/50e9dbc4ab68d94f15261ddc26c8ca2b-Abstract-Conference.html conf/nips/2025 db/conf/nips/neurips2025.html#GaoZDCZQLSCYY25 Haozhi Han Kun Li 0016 Wei Cui Donglin Bai Yiwei Zhang 0009 Liang Yuan Yifeng Chen Yunquan Zhang Ting Cao 0003 Mao Yang 0004 FlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units. 355-368 2025 PPoPP https://doi.org/10.1145/3710848.3710897 conf/ppopp/2025 db/conf/ppopp/ppopp2025.html#HanLCBZYCZCY25 Yiwei Zhang 0009 Kun Li 0016 Liang Yuan Haozhi Han Yunquan Zhang Ting Cao 0003 Mao Yang 0004 Jigsaw: Toward Conflict-free Vectorized Stencil Computation by Tessellating Swizzled Registers. 481-495 2025 PPoPP https://doi.org/10.1145/3710848.3710886 conf/ppopp/2025 db/conf/ppopp/ppopp2025.html#ZhangLYHZCY25 Qi Li 0039 Kun Li 0016 Haozhi Han Liang Yuan Yunquan Zhang Yifeng Chen Junshi Chen 0003 Hong An Ting Cao 0003 Mao Yang 0004 SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation. 1495-1509 2025 SC https://doi.org/10.1145/3712285.3759820 conf/sc/2025 db/conf/sc/sc2025.html#Li0HYZCCA0025 Haozhi Han Kun Li 0016 Fusong Ju Qi Li 0039 Hong An Yifeng Chen Yunquan Zhang Ting Cao 0003 Mao Yang 0004 Matrix Is All You Need: Rearchitecting Quantum Chemistry to Scale on AI Accelerators. 2126-2142 2025 SC https://doi.org/10.1145/3712285.3759829 conf/sc/2025 db/conf/sc/sc2025.html#Han0JLACZ0025 Shenghong Dai Shiqi Jiang 0002 Yifan Yang 0004 Ting Cao 0003 Mo Li 0001 Suman Banerjee 0001 Lili Qiu Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment. 240-253 2025 SenSys https://doi.org/10.1145/3715014.3722068 conf/sensys/2025 db/conf/sensys/sensys2025.html#DaiJYCLBQ25 Tuowei Wang Xingyu Chen Kun Li 0016 Ting Cao 0003 Ju Ren 0001 Yaoxue Zhang JENGA: Enhancing LLM Long-Context Fine-tuning with Contextual Token Sparsity. 123-141 2025 USENIX ATC https://www.usenix.org/conference/atc25/presentation/wang-tuowei conf/usenix/2025 db/conf/usenix/usenix2025.html#WangCLC0Z25

Xin Ding Shijie Cao Ting Cao 0003 Zhibo Chen 0012 Dissecting Bit-Level Scaling Laws in Quantizing Vision Generative Models. 2025 January abs/2501.06218 CoRR https://doi.org/10.48550/arXiv.2501.06218 db/journals/corr/corr2501.html#abs-2501-06218 streams/journals/corr

Tuowei Wang Xingyu Chen Kun Li 0016 Ting Cao 0003 Ju Ren 0001 Yaoxue Zhang LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning. 2025 January abs/2501.09767 CoRR https://doi.org/10.48550/arXiv.2501.09767 db/journals/corr/corr2501.html#abs-2501-09767 streams/journals/corr

Guoyu Li Shengyu Ye Chunyun Chen Yang Wang 0053 Fan Yang 0024 Ting Cao 0003 Cheng Li 0001 Mohamed M. Sabry Mao Yang 0004 LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator. 2025 January abs/2501.10658 CoRR https://doi.org/10.48550/arXiv.2501.10658 db/journals/corr/corr2501.html#abs-2501-10658 streams/journals/corr

Xin Ding Hao Wu 0067 Yifan Yang 0004 Shiqi Jiang 0002 Donglin Bai Zhibo Chen 0012 Ting Cao 0003 StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition. 2025 March abs/2503.06220 CoRR https://doi.org/10.48550/arXiv.2503.06220 db/journals/corr/corr2503.html#abs-2503-06220 streams/journals/corr

Gaole Dai Shiqi Jiang 0002 Ting Cao 0003 Yuanchun Li 0003 Yuqing Yang 0001 Rui Tan 0001 Mo Li 0001 Lili Qiu Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment. 2025 March abs/2503.15937 CoRR https://doi.org/10.48550/arXiv.2503.15937 db/journals/corr/corr2503.html#abs-2503-15937 streams/journals/corr

Dayou Du Shijie Cao Jianyi Cheng Ting Cao 0003 Mao Yang 0004 BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache. 2025 March abs/2503.18773 CoRR https://doi.org/10.48550/arXiv.2503.18773 db/journals/corr/corr2503.html#abs-2503-18773 streams/journals/corr

Tatsuya Kubo Daichi Tokuda Tomoya Nagatani Masayuki Usui Lei Qu Ting Cao 0003 Shinya Takamaeda-Yamazaki MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM Acceleration. 2025 March abs/2503.23817 CoRR https://doi.org/10.48550/arXiv.2503.23817 db/journals/corr/corr2503.html#abs-2503-23817 streams/journals/corr

Fucheng Jia Zewen Wu Shiqi Jiang 0002 Huiqiang Jiang Qianxi Zhang Yuqing Yang 0001 Yunxin Liu 0001 Ju Ren 0001 Deyu Zhang Ting Cao 0003 Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash. 2025 April abs/2504.08378 CoRR https://doi.org/10.48550/arXiv.2504.08378 db/journals/corr/corr2504.html#abs-2504-08378 streams/journals/corr

Yuxuan Yan Shiqi Jiang 0002 Ting Cao 0003 Yifan Yang 0004 Qianqian Yang 0002 Yuanchao Shu Yuqing Yang 0001 Lili Qiu Empowering Agentic Video Analytics Systems with Video Language Models. 2025 May abs/2505.00254 CoRR https://doi.org/10.48550/arXiv.2505.00254 db/journals/corr/corr2505.html#abs-2505-00254 streams/journals/corr

Jiaxu Qian Chendong Wang Yifan Yang 0004 Chaoyun Zhang Huiqiang Jiang Xufang Luo Yu Kang 0006 Qingwei Lin Anlan Zhang Shiqi Jiang 0002 Ting Cao 0003 Tianjun Mao Suman Banerjee 0001 Guyue Liu Saravan Rajmohan Dongmei Zhang 0001 Yuqing Yang 0001 Qi Zhang 0066 Lili Qiu Zoomer: Adaptive Image Focus Optimization for Black-box MLLM. 2025 May abs/2505.00742 CoRR https://doi.org/10.48550/arXiv.2505.00742 db/journals/corr/corr2505.html#abs-2505-00742 streams/journals/corr

Tatsuya Kubo Daichi Tokuda Lei Qu Ting Cao 0003 Shinya Takamaeda-Yamazaki PUDTune: Multi-Level Charging for High-Precision Calibration in Processing-Using-DRAM. 2025 May abs/2505.05266 CoRR https://doi.org/10.48550/arXiv.2505.05266 db/journals/corr/corr2505.html#abs-2505-05266 streams/journals/corr

Qi Li 0039 Kun Li 0016 Haozhi Han Honghui Shang Xinfu He Yunquan Zhang Hong An Ting Cao 0003 Mao Yang 0004 SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale. 2025 May abs/2505.20094 CoRR https://doi.org/10.48550/arXiv.2505.20094 db/journals/corr/corr2505.html#abs-2505-20094 streams/journals/corr

Yizhao Gao 0002 Shuming Guo Shijie Cao Yuqing Xia Yu Cheng 0030 Lei Wang 0222 Lingxiao Ma Yutao Sun Tianzhu Ye Li Dong 0004 Hayden Kwok-Hay So Yu Hua 0001 Ting Cao 0003 Fan Yang 0024 Mao Yang 0004 SeerAttention-R: Sparse Attention Adaptation for Long Reasoning. 2025 June abs/2506.08889 CoRR https://doi.org/10.48550/arXiv.2506.08889 db/journals/corr/corr2506.html#abs-2506-08889 streams/journals/corr

Qi Li 0039 Kun Li 0016 Haozhi Han Liang Yuan Junshi Chen 0003 Yunquan Zhang Yifeng Chen Hong An Ting Cao 0003 Mao Yang 0004 SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation. 2025 June abs/2506.22969 CoRR https://doi.org/10.48550/arXiv.2506.22969 db/journals/corr/corr2506.html#abs-2506-22969 streams/journals/corr

Gaole Dai Shiqi Jiang 0002 Ting Cao 0003 Yuqing Yang 0001 Yuanchun Li 0003 Rui Tan 0001 Mo Li 0001 Lili Qiu ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration. 2025 September abs/2509.21823 CoRR https://doi.org/10.48550/arXiv.2509.21823 db/journals/corr/corr2509.html#abs-2509-21823 streams/journals/corr

Zixu Hao Jianyu Wei Tuowei Wang Minxing Huang Huiqiang Jiang Shiqi Jiang 0002 Ting Cao 0003 Ju Ren 0001 Scaling LLM Test-Time Compute with Mobile NPU on Smartphones. 2025 September abs/2509.23324 CoRR https://doi.org/10.48550/arXiv.2509.23324 db/journals/corr/corr2509.html#abs-2509-23324 streams/journals/corr

Xin Ding Jianyu Wei Yifan Yang 0004 Shiqi Jiang 0002 Qianxi Zhang Hao Wu 0067 Fucheng Jia Liang Mi Yuxuan Yan Weijun Wang 0001 Yunxin Liu 0001 Zhibo Chen 0001 Ting Cao 0003 AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation. 2025 September abs/2509.24387 CoRR https://doi.org/10.48550/arXiv.2509.24387 db/journals/corr/corr2509.html#abs-2509-24387 streams/journals/corr

Chendong Wang Donglin Bai Yifan Yang 0004 Xiao Jin Anlan Zhang Rui Wang 0095 Shiqi Jiang 0002 Yuqing Yang 0001 Hao Wu 0067 Qi Dai 0001 Chong Luo 0001 Ting Cao 0003 Lili Qiu Suman Banerjee 0001 Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning. 2025 October abs/2510.04022 CoRR https://doi.org/10.48550/arXiv.2510.04022 db/journals/corr/corr2510.html#abs-2510-04022 streams/journals/corr

Tuowei Wang Kun Li 0016 Zixu Hao Donglin Bai Ju Ren 0001 Yaoxue Zhang Ting Cao 0003 Mao Yang 0004 Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity. 2025 October abs/2510.15964 CoRR https://doi.org/10.48550/arXiv.2510.15964 db/journals/corr/corr2510.html#abs-2510-15964 streams/journals/corr

Jianyu Wei Qingtao Li Shijie Cao Lingxiao Ma Zixu Hao Yanyong Zhang Xiaoyan Hu Ting Cao 0003 T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table Lookup. 2025 November abs/2511.11248 CoRR https://doi.org/10.48550/arXiv.2511.11248 db/journals/corr/corr2511.html#abs-2511-11248 streams/journals/corr

Jinrui Zhang Huan Yang Ju Ren 0001 Deyu Zhang Bangwen He Youngki Lee 0001 Ting Cao 0003 Yuanchun Li 0003 Yaoxue Zhang Yunxin Liu 0001 HiMoDepth: Efficient Training-Free High-Resolution On-Device Depth Perception. 4648-4664 2024 May 23 IEEE Trans. Mob. Comput. 5 https://doi.org/10.1109/TMC.2023.3294188 db/journals/tmc/tmc23.html#ZhangYRZHLCLZL24

Yijia Zhang Sicheng Zhang Shijie Cao Dayou Du Jianyu Wei Ting Cao 0003 Ningyi Xu AFPQ: Asymmetric Floating Point Quantization for LLMs. 28-36 2024 ACL (Findings) https://doi.org/10.18653/v1/2024.findings-acl.3 https://aclanthology.org/2024.findings-acl.3 conf/acl/2024f db/conf/acl/acl2024f.html#ZhangZCDWCX24 Dayou Du Yijia Zhang Shijie Cao Jiaqi Guo Ting Cao 0003 Xiaowen Chu 0001 Ningyi Xu BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation. 102-116 2024 ACL (1) https://doi.org/10.18653/v1/2024.acl-long.7 https://aclanthology.org/2024.acl-long.7 https://www.wikidata.org/entity/Q131457613 conf/acl/2024-1 db/conf/acl/acl2024-1.html#DuZCGCCX24 Cong Li 0008 Zhe Zhou 0002 Yang Wang 0053 Fan Yang 0093 Ting Cao 0003 Mao Yang 0004 Yun Liang 0001 Guangyu Sun 0003 PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization. 879-896 2024 ASPLOS (2) https://doi.org/10.1145/3620665.3640376 https://www.wikidata.org/entity/Q130929425 conf/asplos/2024-2 db/conf/asplos/asplos2024-2.html#LiZWYCYL024 Zixu Hao Huiqiang Jiang Shiqi Jiang 0002 Ju Ren 0001 Ting Cao 0003 Hybrid SLM and LLM for Edge-Cloud Collaborative Inference. 36-41 2024 EdgeFM@MobiSys https://doi.org/10.1145/3662006.3662067 https://www.wikidata.org/entity/Q130817130 conf/edgefm/2024 db/conf/edgefm/edgefm2024.html#HaoJJ0C24 Yifei Liu Jicheng Wen Yang Wang 0053 Shengyu Ye Li Lyna Zhang Ting Cao 0003 Cheng Li 0001 Mao Yang 0004 VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models. 8181-8196 2024 EMNLP https://doi.org/10.18653/v1/2024.emnlp-main.467 https://aclanthology.org/2024.emnlp-main.467 conf/emnlp/2024 db/conf/emnlp/emnlp2024.html#LiuW0YZC0024 Yijia Zhang Lingran Zhao Shijie Cao Sicheng Zhang Wenqiang Wang Ting Cao 0003 Fan Yang 0024 Mao Yang 0004 Shanghang Zhang Ningyi Xu Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models. 1-6 2024 ICME https://doi.org/10.1109/ICME57554.2024.10688089 conf/icmcs/2024 db/conf/icmcs/icme2024.html#ZhangZCZWCYYZX24 Ranggi Hwang Jianyu Wei Shijie Cao Changho Hwang Xiaohu Tang 0003 Ting Cao 0003 Mao Yang 0004 Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference. 1018-1031 2024 ISCA https://doi.org/10.1109/ISCA59077.2024.00078 conf/isca/2024 db/conf/isca/isca2024.html#HwangWCHTCY24 streams/conf/isca Xiangyu Li Yuanchun Li 0003 Yuanzhe Li 0001 Ting Cao 0003 Yunxin Liu 0001 FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices. 709-723 2024 MobiCom https://doi.org/10.1145/3636534.3649391 https://www.wikidata.org/entity/Q130953131 conf/mobicom/2024 db/conf/mobicom/mobicom2024.html#LiLLCL24 Fucheng Jia Shiqi Jiang 0002 Ting Cao 0003 Wei Cui Tianrui Xia Xu Cao Yuanchun Li 0003 Qipeng Wang 0001 Deyu Zhang Ju Ren 0001 Yunxin Liu 0001 Lili Qiu Mao Yang 0004 Empowering In-Browser Deep Learning Inference on Edge Through Just-In-Time Kernel Optimization. 438-450 2024 MobiSys https://doi.org/10.1145/3643832.3661892 https://www.wikidata.org/entity/Q130935701 conf/mobisys/2024 db/conf/mobisys/mobisys2024.html#JiaJCCXCLWZ0LQY24 Jeongho Won Ting Cao 0003 Huiqiang Jiang Junehwa Song Poster: Design of Elastic Deep Neural Network Candidate Spaces for Inference on Diverse Devices. 734-735 2024 MobiSys https://doi.org/10.1145/3643832.3661445 https://www.wikidata.org/entity/Q130955968 conf/mobisys/2024 db/conf/mobisys/mobisys2024.html#WonCJS24 Chengquan Feng Li Lyna Zhang Yuanchi Liu Jiahang Xu Chengruidong Zhang Zhiyuan Wang Ting Cao 0003 Mao Yang 0004 Haisheng Tan LitePred: Transferable and Scalable Latency Prediction for Hardware-Aware Neural Architecture Search. 2024 NSDI https://www.usenix.org/conference/nsdi24/presentation/feng-chengquan conf/nsdi/2024 db/conf/nsdi/nsdi2024.html#FengZLXZWCYT24 Lei Wang 0222 Lingxiao Ma Shijie Cao Quanlu Zhang Jilong Xue Yining Shi 0001 Ningxin Zheng Ziming Miao Fan Yang 0024 Ting Cao 0003 Yuqing Yang 0001 Mao Yang 0004 Ladder: Enabling Efficient Low-Precision Deep Learning Computing through Hardware-aware Tensor Transformation. 307-323 2024 OSDI https://www.usenix.org/conference/osdi24/presentation/wang-lei conf/osdi/2024 db/conf/osdi/osdi2024.html#WangMCZX0ZM0C0Y24 Yuetao Chen Kun Li 0016 Yuhao Wang Donglin Bai Lei Wang 0222 Lingxiao Ma Liang Yuan Yunquan Zhang Ting Cao 0003 Mao Yang 0004 ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores. 333-347 2024 PPoPP https://doi.org/10.1145/3627535.3638476 https://www.wikidata.org/entity/Q131127563 conf/ppopp/2024 db/conf/ppopp/ppopp2024.html#ChenLWBWMYZCY24 Tuowei Wang Kun Li 0016 Zixu Hao Donglin Bai Ju Ren 0001 Yaoxue Zhang Ting Cao 0003 Mao Yang 0004 Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity. 75 2024 SC https://doi.org/10.1109/SC41406.2024.00081 https://dl.acm.org/doi/10.1109/SC41406.2024.00081 conf/sc/2024 db/conf/sc/sc2024.html#WangLHB0ZCY24 Yiwei Zhang 0009 Kun Li 0016 Liang Yuan Jiawen Cheng Yunquan Zhang Ting Cao 0003 Mao Yang 0004 LoRAStencil: Low-Rank Adaptation of Stencil Computation on Tensor Cores. 53 2024 SC https://doi.org/10.1109/SC41406.2024.00059 https://dl.acm.org/doi/10.1109/SC41406.2024.00059 conf/sc/2024 db/conf/sc/sc2024.html#ZhangLYCZCY24

Qipeng Wang 0001 Shiqi Jiang 0002 Zhenpeng Chen 0001 Xu Cao Yuanchun Li 0003 Aoyu Li Ying Zhang 0012 Yun Ma 0002 Ting Cao 0003 Xuanzhe Liu Exploring the Impact of In-Browser Deep Learning Inference on Quality of User Experience and Performance. 2024 abs/2402.05981 CoRR https://doi.org/10.48550/arXiv.2402.05981 db/journals/corr/corr2402.html#abs-2402-05981

Dayou Du Yijia Zhang Shijie Cao Jiaqi Guo Ting Cao 0003 Xiaowen Chu 0001 Ningyi Xu BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation. 2024 abs/2402.10631 CoRR https://doi.org/10.48550/arXiv.2402.10631 db/journals/corr/corr2402.html#abs-2402-10631

Jianyu Wei Shijie Cao Ting Cao 0003 Lingxiao Ma Lei Wang 0222 Yanyong Zhang Mao Yang 0004 T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge. 2024 abs/2407.00088 CoRR https://doi.org/10.48550/arXiv.2407.00088 db/journals/corr/corr2407.html#abs-2407-00088 streams/journals/corr

Shenghong Dai Shiqi Jiang 0002 Yifan Yang 0004 Ting Cao 0003 Mo Li 0001 Suman Banerjee 0001 Lili Qiu Advancing Multi-Modal Sensing Through Expandable Modality Alignment. 2024 abs/2407.17777 CoRR https://doi.org/10.48550/arXiv.2407.17777 db/journals/corr/corr2407.html#abs-2407-17777 streams/journals/corr

Zhiwen Mo Lei Wang 0222 Jianyu Wei Zhichen Zeng 0002 Shijie Cao Lingxiao Ma Naifeng Jing Ting Cao 0003 Jilong Xue Fan Yang 0024 Mao Yang 0004 LUT Tensor Core: Lookup Table Enables Efficient Low-Bit LLM Inference Acceleration. 2024 abs/2408.06003 CoRR https://doi.org/10.48550/arXiv.2408.06003 db/journals/corr/corr2408.html#abs-2408-06003 streams/journals/corr

Yifei Liu Jicheng Wen Yang Wang 0053 Shengyu Ye Li Lyna Zhang Ting Cao 0003 Cheng Li 0001 Mao Yang 0004 VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models. 2024 abs/2409.17066 CoRR https://doi.org/10.48550/arXiv.2409.17066 db/journals/corr/corr2409.html#abs-2409-17066 streams/journals/corr

Yizhao Gao 0002 Zhichen Zeng 0002 Dayou Du Shijie Cao Hayden Kwok-Hay So Ting Cao 0003 Fan Yang 0024 Mao Yang 0004 SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs. 2024 abs/2410.13276 CoRR https://doi.org/10.48550/arXiv.2410.13276 db/journals/corr/corr2410.html#abs-2410-13276 streams/journals/corr

Hao Wu 0067 Donglin Bai Shiqi Jiang 0002 Qianxi Zhang Yifan Yang 0004 Ting Cao 0003 Fengyuan Xu Making Every Frame Matter: Continuous Video Understanding for Large Models via Adaptive State Modeling. 2024 abs/2410.14993 CoRR https://doi.org/10.48550/arXiv.2410.14993 db/journals/corr/corr2410.html#abs-2410-14993 streams/journals/corr

Tuowei Wang Ruwen Fan Minxing Huang Zixu Hao Kun Li 0016 Ting Cao 0003 Youyou Lu Yaoxue Zhang Ju Ren 0001 Ripple: Accelerating LLM Inference on Smartphones with Correlation-Aware Neuron Management. 2024 abs/2410.19274 CoRR https://doi.org/10.48550/arXiv.2410.19274 db/journals/corr/corr2410.html#abs-2410-19274 streams/journals/corr

Tuowei Wang Kun Li 0016 Donglin Bai Fusong Ju Leo Xia Ting Cao 0003 Ju Ren 0001 Yaoxue Zhang Mao Yang 0004 Matryoshka: Optimization of Dynamic Diverse Quantum Chemistry Systems via Elastic Parallelism Transformation. 2024 abs/2412.13203 CoRR https://doi.org/10.48550/arXiv.2412.13203 db/journals/corr/corr2412.html#abs-2412-13203 streams/journals/corr

Yijia Zhang Yibo Han Shijie Cao Guohao Dai 0001 Youshan Miao Ting Cao 0003 Fan Yang 0024 Ningyi Xu Adam Accumulation to Reduce Memory Footprints of Both Activations and Gradients for Large-Scale DNN Training. 3058-3065 2023 ECAI https://doi.org/10.3233/FAIA230623 conf/ecai/2023 db/conf/ecai/ecai2023.html#ZhangHCDMCYX23 Xudong Wang Li Lyna Zhang Jiahang Xu Quanlu Zhang Yujing Wang 0002 Yuqing Yang 0001 Ningxin Zheng Ting Cao 0003 Mao Yang 0004 SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference. 5796-5805 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.00535 conf/iccv/2023 db/conf/iccv/iccv2023.html#WangZXZW0ZCY23 Chen Tang Li Lyna Zhang Huiqiang Jiang Jiahang Xu Ting Cao 0003 Quanlu Zhang Yuqing Yang 0001 Zhi Wang Mao Yang 0004 ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices. 5806-5817 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.00536 conf/iccv/2023 db/conf/iccv/iccv2023.html#TangZJXCZYWY23 Junyan Li Li Lyna Zhang Jiahang Xu Yujing Wang 0002 Shaoguang Yan Yunqing Xia Yuqing Yang 0001 Ting Cao 0003 Hao Sun 0015 Weiwei Deng Qi Zhang 0066 Mao Yang 0004 Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference. 1280-1290 2023 KDD https://doi.org/10.1145/3580305.3599284 https://www.wikidata.org/entity/Q130937514 conf/kdd/2023 db/conf/kdd/kdd2023.html#LiZXWYXYC0DZY23 Bin Lin Ningxin Zheng Lei Wang 0222 Shijie Cao Lingxiao Ma Quanlu Zhang Yi Zhu Ting Cao 0003 Jilong Xue Yuqing Yang 0001 Fan Yang 0024 Efficient GPU Kernels for N: M-Sparse Weights in Deep Learning. 2023 MLSys https://proceedings.mlsys.org/paper_files/paper/2023/hash/a10deb4d5227a8ea307ea8ff3cb712f4-Abstract-mlsys2023.html conf/mlsys/2023 db/conf/mlsys/mlsys2023.html#LinZWCMZZCX0023 Xiaohu Tang 0003 Yang Wang 0053 Ting Cao 0003 Li Lyna Zhang Qi Chen 0009 Deng Cai 0001 Yunxin Liu 0001 Mao Yang 0004 LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup. 70:1-70:15 2023 MobiCom https://doi.org/10.1145/3570361.3613285 https://www.wikidata.org/entity/Q130958014 conf/mobicom/2023 db/conf/mobicom/mobicom2023.html#TangWCZC0LY23 Jianyu Wei Ting Cao 0003 Shijie Cao Shiqi Jiang 0002 Shaowei Fu Mao Yang 0004 Yanyong Zhang Yunxin Liu 0001 NN-Stretch: Automatic Neural Network Branching for Parallel Inference on Heterogeneous Multi-Processors. 70-83 2023 MobiSys https://doi.org/10.1145/3581791.3596870 https://www.wikidata.org/entity/Q130964321 conf/mobisys/2023 db/conf/mobisys/mobisys2023.html#WeiCCJFYZL23 Rongjie Yi Ting Cao 0003 Ao Zhou 0001 Xiao Ma 0009 Shangguang Wang Mengwei Xu 0001 Boosting DNN Cold Inference on Edge Devices. 516-529 2023 MobiSys https://doi.org/10.1145/3581791.3596842 conf/mobisys/2023 db/conf/mobisys/mobisys2023.html#YiC0MWX23

Xiaohu Tang 0003 Yang Wang 0053 Ting Cao 0003 Li Lyna Zhang Qi Chen 0009 Deng Cai 0001 Yunxin Liu 0001 Mao Yang 0004 LUT-NN: Towards Unified Neural Network Inference by Table Lookup. 2023 abs/2302.03213 CoRR https://doi.org/10.48550/arXiv.2302.03213 db/journals/corr/corr2302.html#abs-2302-03213

Li Lyna Zhang Xudong Wang Jiahang Xu Quanlu Zhang Yujing Wang 0002 Yuqing Yang 0001 Ningxin Zheng Ting Cao 0003 Mao Yang 0004 SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference. 2023 abs/2303.08308 CoRR https://doi.org/10.48550/arXiv.2303.08308 db/journals/corr/corr2303.html#abs-2303-08308

Kun Li 0016 Zhichun Li Yuetao Chen Zixuan Wang Yiwei Zhang 0009 Liang Yuan Haipeng Jia Yunquan Zhang Ting Cao 0003 Mao Yang 0004 Gamify Stencil Dwarf on Cloud for Democratizing Scientific Computing. 2023 abs/2303.08365 CoRR https://doi.org/10.48550/arXiv.2303.08365 db/journals/corr/corr2303.html#abs-2303-08365

Chen Tang Li Lyna Zhang Huiqiang Jiang Jiahang Xu Ting Cao 0003 Quanlu Zhang Yuqing Yang 0001 Zhi Wang Mao Yang 0004 ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices. 2023 abs/2303.09730 CoRR https://doi.org/10.48550/arXiv.2303.09730 db/journals/corr/corr2303.html#abs-2303-09730

Yijia Zhang Lingran Zhao Shijie Cao Wenqiang Wang Ting Cao 0003 Fan Yang 0024 Mao Yang 0004 Shanghang Zhang Ningyi Xu Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models. 2023 abs/2305.12356 CoRR https://doi.org/10.48550/arXiv.2305.12356 db/journals/corr/corr2305.html#abs-2305-12356

Yijia Zhang Yibo Han Shijie Cao Guohao Dai 0001 Youshan Miao Ting Cao 0003 Fan Yang 0024 Ningyi Xu Adam Accumulation to Reduce Memory Footprints of both Activations and Gradients for Large-scale DNN Training. 2023 abs/2305.19982 CoRR https://doi.org/10.48550/arXiv.2305.19982 db/journals/corr/corr2305.html#abs-2305-19982

Junyan Li Li Lyna Zhang Jiahang Xu Yujing Wang 0002 Shaoguang Yan Yunqing Xia Yuqing Yang 0001 Ting Cao 0003 Hao Sun 0015 Weiwei Deng Qi Zhang 0066 Mao Yang 0004 Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference. 2023 abs/2306.14393 CoRR https://doi.org/10.48550/arXiv.2306.14393 db/journals/corr/corr2306.html#abs-2306-14393

Ranggi Hwang Jianyu Wei Shijie Cao Changho Hwang Xiaohu Tang 0003 Ting Cao 0003 Mao Yang 0004 Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference. 2023 abs/2308.12066 CoRR https://doi.org/10.48550/arXiv.2308.12066 db/journals/corr/corr2308.html#abs-2308-12066

Fucheng Jia Shiqi Jiang 0002 Ting Cao 0003 Wei Cui Tianrui Xia Xu Cao Yuanchun Li 0003 Deyu Zhang Ju Ren 0001 Yunxin Liu 0001 Lili Qiu Mao Yang 0004 Accelerating In-Browser Deep Learning Inference on Diverse Edge Clients through Just-in-Time Kernel Optimizations. 2023 abs/2309.08978 CoRR https://doi.org/10.48550/arXiv.2309.08978 db/journals/corr/corr2309.html#abs-2309-08978

Yijia Zhang Sicheng Zhang Shijie Cao Dayou Du Jianyu Wei Ting Cao 0003 Ningyi Xu AFPQ: Asymmetric Floating Point Quantization for LLMs. 2023 abs/2311.01792 CoRR https://doi.org/10.48550/arXiv.2311.01792 db/journals/corr/corr2311.html#abs-2311-01792

Li Lyna Zhang Youkow Homma Yujing Wang 0002 Min Wu Mao Yang 0004 Ruofei Zhang Ting Cao 0003 Wei Shen SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance. 3654-3663 2022 CIKM https://doi.org/10.1145/3511808.3557139 conf/cikm/2022 db/conf/cikm/cikm2022.html#ZhangHWWYZCS22 Rendong Liang Ting Cao 0003 Jicheng Wen Manni Wang Yang Wang 0053 Jianhua Zou Yunxin Liu 0001 Romou: rapidly generate high-performance tensor kernels for mobile GPUs. 487-500 2022 MobiCom https://doi.org/10.1145/3495243.3517020 conf/mobicom/2022 db/conf/mobicom/mobicom2022.html#LiangCWWWZL22 Jinrui Zhang Huan Yang Ju Ren 0001 Deyu Zhang Bangwen He Ting Cao 0003 Yuanchun Li 0003 Yaoxue Zhang Yunxin Liu 0001 MobiDepth: real-time depth estimation using on-device dual cameras. 528-541 2022 MobiCom https://doi.org/10.1145/3495243.3560517 conf/mobicom/2022 db/conf/mobicom/mobicom2022.html#ZhangYRZHCLZL22 Fucheng Jia Deyu Zhang Ting Cao 0003 Shiqi Jiang 0002 Yunxin Liu 0001 Ju Ren 0001 Yaoxue Zhang CoDL: efficient CPU-GPU co-execution for deep learning inference on mobile devices. 209-221 2022 MobiSys https://doi.org/10.1145/3498361.3538932 conf/mobisys/2022 db/conf/mobisys/mobisys2022.html#JiaZCJLRZ22 Yan Lu 0006 Shiqi Jiang 0002 Ting Cao 0003 Yuanchao Shu Turbo: Opportunistic Enhancement for Edge Video Analytics. 263-276 2022 SenSys https://doi.org/10.1145/3560905.3568501 conf/sensys/2022 db/conf/sensys/sensys2022.html#0006JCS22 Ziyan Fu 0001 Ju Ren 0001 Yunxin Liu 0001 Ting Cao 0003 Deyu Zhang Yuezhi Zhou Yaoxue Zhang Hyperion: A Generic and Distributed Mobile Offloading Framework on OpenCL. 607-621 2022 SenSys https://doi.org/10.1145/3560905.3568511 conf/sensys/2022 db/conf/sensys/sensys2022.html#FuRLCZZZ22

Rongjie Yi Ting Cao 0003 Ao Zhou 0001 Xiao Ma 0009 Shangguang Wang Mengwei Xu 0001 Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices. 2022 abs/2206.07446 CoRR https://doi.org/10.48550/arXiv.2206.07446 db/journals/corr/corr2206.html#abs-2206-07446

Yan Lu 0006 Shiqi Jiang 0002 Ting Cao 0003 Yuanchao Shu Turbo: Opportunistic Enhancement for Edge Video Analytics. 2022 abs/2207.00172 CoRR https://doi.org/10.48550/arXiv.2207.00172 db/journals/corr/corr2207.html#abs-2207-00172

Li Lyna Zhang Youkow Homma Yujing Wang 0002 Min Wu Mao Yang 0004 Ruofei Zhang Ting Cao 0003 Wei Shen SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance. 2022 abs/2209.00625 CoRR https://doi.org/10.48550/arXiv.2209.00625 db/journals/corr/corr2209.html#abs-2209-00625

Li Lyna Zhang Shihao Han Jianyu Wei Ningxin Zheng Ting Cao 0003 Yunxin Liu 0001 nn-METER: Towards Accurate Latency Prediction of DNN Inference on Diverse Edge Devices. 19-23 2021 25 GetMobile Mob. Comput. Commun. 4 https://doi.org/10.1145/3529706.3529712 db/journals/sigmobile/sigmobile25.html#ZhangHWZCL21

Xiaohu Tang 0003 Shihao Han Li Lyna Zhang Ting Cao 0003 Yunxin Liu 0001 To Bridge Neural Network Design and Real-World Performance: A Behaviour Study for Neural Networks. 2021 MLSys https://proceedings.mlsys.org/paper_files/paper/2021/hash/411e39b117e885341f25efb8912945f7-Abstract.html conf/mlsys/2021 db/conf/mlsys/mlsys2021.html#TangHZCL21 Manni Wang Shaohua Ding Ting Cao 0003 Yunxin Liu 0001 Fengyuan Xu AsyMo: scalable and efficient deep-learning inference on asymmetric mobile CPUs. 215-228 2021 MobiCom https://doi.org/10.1145/3447993.3448625 conf/mobicom/2021 db/conf/mobicom/mobicom2021.html#WangDCLX21 Li Lyna Zhang Shihao Han Jianyu Wei Ningxin Zheng Ting Cao 0003 Yuqing Yang 0001 Yunxin Liu 0001 nn-Meter: towards accurate latency prediction of deep-learning model inference on diverse edge devices. 81-93 2021 MobiSys https://doi.org/10.1145/3458864.3467882 conf/mobisys/2021 db/conf/mobisys/mobisys2021.html#ZhangHWZCYL21 Shiqi Jiang 0002 Lihao Ran Ting Cao 0003 Yusen Xu Yunxin Liu 0001 Profiling and optimizing deep learning inference on mobile GPUs. 75-81 2020 APSys https://doi.org/10.1145/3409963.3410493 conf/apsys/2020 db/conf/apsys/apsys2020.html#JiangRCXL20 Hong An Donglin Bai Suman Banerjee 0001 Deng Cai 0001 Shijie Cao Xu Cao Chunyun Chen Haoquan Chen Jinghan Chen Junshi Chen 0003 Qi Chen 0009 Xingyu Chen Yifeng Chen Yuetao Chen Zhenpeng Chen 0001 Zhibo Chen 0001 Zhibo Chen 0012 Jianyi Cheng Jiawen Cheng Yu Cheng 0030 Xiaowen Chu 0001 Wei Cui Gaole Dai Guohao Dai 0001 Haipeng Dai 0001 Qi Dai 0001 Shenghong Dai Weiwei Deng Shaohua Ding Xin Ding Li Dong 0004 Dayou Du Ruwen Fan Chengquan Feng Shaowei Fu Ziyan Fu 0001 Yizhao Gao 0002 Jiaqi Guo Shuming Guo Haozhi Han Shihao Han Yibo Han Zixu Hao Bangwen He Xinfu He Youkow Homma Xiaoyan Hu Yu Hua 0001 Bingjia Huang Mingzhe Huang Minxing Huang Changho Hwang Ranggi Hwang Fucheng Jia Haipeng Jia Huiqiang Jiang Shiqi Jiang 0002 Xiao Jin Naifeng Jing Fusong Ju Ruofei Ju Yu Kang 0006 Tatsuya Kubo Junjie Lai Youngki Lee 0001 Aoyu Li Cheng Li 0001 Cong Li 0008 Guoyu Li Junyan Li Kun Li 0016 Mo Li 0001 Qi Li 0039 Qingtao Li Xiangyu Li Yuanchun Li 0001 Yuanchun Li 0003 Yuanzhe Li 0001 Zhichun Li Rendong Liang Yun Liang 0001 Bin Lin Qingwei Lin Cheng Liu 0008 Guyue Liu Ruiqi Liu 0001 Xuanzhe Liu Yifei Liu Yuanchi Liu Yunxin Liu 0001 Yan Lu 0006 Youyou Lu Chong Luo 0001 Xufang Luo Lingxiao Ma Xiao Ma 0009 Yun Ma 0002 Luo Mai Tianjun Mao Liang Mi Youshan Miao Ziming Miao Zhiwen Mo Tomoya Nagatani Lichen Pang Jiaxing Qi Jiaxu Qian Lili Qiu Lei Qu Saravan Rajmohan Lihao Ran Ju Ren 0001 Mohamed M. SabryMohamed M. Sabry Aly Honghui Shang Wei Shen Yining Shi 0001 Yuanchao Shu Hayden Kwok-Hay SoHayden K. H. So Junehwa Song Guangyu Sun 0003 Hao Sun 0015 Yutao Sun Shinya Takamaeda-Yamazaki Haisheng Tan Rui Tan 0001 Chen Tang Xiaohu Tang 0003 Daichi Tokuda Masayuki Usui Chendong Wang Lei Wang 0222 Manni Wang Qipeng Wang 0001 Rui Wang 0095 Shangguang Wang Tuowei Wang Wei Wang 0002 Weijun Wang 0001 Wenqiang Wang Xiang Wang Xianye Wang Xinrui Wang Xudong Wang Yang Wang 0053 Yuhao Wang Yujing Wang 0002 Zhi Wang Zhiyuan Wang Zixuan Wang Jianyu Wei Hao Wen 0004 Jicheng Wen Jeongho Won Hao Wu 0067 Min Wu Zewen Wu Leo Xia Tianrui Xia Yunqing Xia Yuqing Xia Fengyuan Xu Jiahang Xu Mengwei Xu 0001 Ningyi Xu Yusen Xu Jilong Xue Shaoguang Yan Yuxuan Yan Fan Yang 0024 Fan Yang 0093 Huan Yang Mao Yang 0004 Qianqian Yang 0002 Shansong Yang Yifan Yang 0004 Yuqing Yang 0001 Shengyu Ye Tianzhu Ye Rongjie Yi Chengyu Yin Liang Yuan Zhichen Zeng 0002 Anlan Zhang Chaoyun Zhang Chengruidong Zhang Deyu Zhang Dongmei Zhang 0001 Jinrui Zhang Li Lyna Zhang Qi Zhang 0066 Qianxi Zhang Quanlu Zhang Ruge Zhang Ruofei Zhang Shanghang Zhang Sicheng Zhang Ya-Qin Zhang Yanyong Zhang Yaoxue Zhang Yijia Zhang Ying Zhang 0012 Yiwei Zhang 0009 Yunquan Zhang Ziming Zhang Lingran Zhao Ningxin Zheng Yikai Zheng Ao Zhou 0001 Peiyuan Zhou Yue-Zhi ZhouYuezhi Zhou Zhe Zhou 0002 Hanxin Zhu Yi Zhu Jianhua Zou