{"id":11,"date":"2013-08-28T20:31:43","date_gmt":"2013-08-28T20:31:43","guid":{"rendered":"http:\/\/www.rle.mit.edu\/eems\/?page_id=11"},"modified":"2023-11-08T20:27:33","modified_gmt":"2023-11-08T20:27:33","slug":"publications","status":"publish","type":"page","link":"https:\/\/eems.mit.edu\/dev_site\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"<p>This material is presented to ensure the timely dissemination of scholarly and technical work. All persons copying this material are expected to adhere to the terms and constraints invoked by the copyright holder. In most cases, these works may not be reposted without the explicit permission of the copyright holder.<\/p>\n<p><b>* Indicates authors contributed equally to the work<\/b><\/p>\n<p>&nbsp;<\/p>\n<h4>2023<\/h4>\n<ul>\n<li>Z. Y. Xue, Y. N. Wu, J. S. Emer, V. Sze, &#8220;Tailors: Accelerating Sparse Tensor Algebra by Overbooking Buffer Occupancy,&#8221; <i>ACM\/IEEE International Symposium on Microarchitecture (MICRO)<\/i>, Oct 2023. [ paper <a href=\"https:\/\/arxiv.org\/abs\/2310.00192\">arXiv<\/a> | lightning talk <a href=\"https:\/\/www.youtube.com\/watch?v=tX0wxHV09ms\">video<\/a> | project website <a href=\"https:\/\/emze.csail.mit.edu\/tailors\">LINK<\/a> ]<\/li>\n<li>Y. N. Wu, P.-A. Tsai, S. Muralidharan, A. Parashar, V. Sze, J. S. Emer, &#8220;HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity,&#8221; <i>ACM\/IEEE International Symposium on Microarchitecture (MICRO)<\/i>, Oct 2023. [ paper <a href=\"https:\/\/arxiv.org\/abs\/2305.12718\">arXiv<\/a> | lightning talk <a href=\"https:\/\/youtu.be\/x7cS9gczmhw\">video<\/a> | project website <a href=\"https:\/\/emze.csail.mit.edu\/highlight\">LINK<\/a> ]<\/li>\n<li>P. Z. X. Li, S. Karaman, V. Sze, &#8220;GMMap: Memory-Efficient Continuous Occupancy Map Using Gaussian Mixture Model,&#8221; arXiv, June 2023. [ paper <a href=\"https:\/\/arxiv.org\/abs\/2306.03740\">arXiv<\/a> ]<\/li>\n<li>T. Andrulis, J. Emer, V. Sze, &#8220;RAELLA: Reforming the Arithmetic for Efficient, Low-Resolution, and Low-Loss Analog PIM: No Retraining Required!,&#8221; <i>International Symposium on Computer Architecture (ISCA)<\/i>, June 2023. [ paper <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/04\/2023_isca_raella.pdf\">PDF<\/a> | lightning talk <a href=\"https:\/\/www.youtube.com\/watch?v=hUjqdJW4Xyc\">video<\/a> | code <a href=\"https:\/\/github.com\/mit-emze\/raella\"> github<\/a> ]<\/li>\n<li>V. Sivaraman, P. Karimi, V. Venkatapathy, M.Khani, S. Fouladi, M. Alizadeh, F. Durand, V. Sze, &#8220;Gemino: Practical and Robust Neural Compression for Video Conferencing,&#8221; to appear at <i>USENIX Symposium on Networked Systems Design and Implementation (NDSI)<\/i> [ paper <a href=\"https:\/\/arxiv.org\/abs\/2209.10507\">arXiv<\/a> ]<\/li>\n<li>M. Gilbert, Y. N. Wu, A. Parashar, V. Sze, J. Emer, &#8220;LoopTree: Enabling Exploration of Fused-layer Dataflow Accelerators,&#8221; <i>IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)<\/i>, April 2023. [ <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/07\/2023_ispass_looptree.pdf\">PDF<\/a> ]<\/li>\n<li>H.-Y. Lai, C. Sodini, V. Sze, T. Heldt, &#8220;Individualized Tracking of Neurocognitive-State-Dependent Eye-Movement Features Using Mobile Devices,&#8221; <i>Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)<\/i>, Vol. 7, No. 1, pp. 1 &#8211; 23, March 2023. [ <a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3580843\">LINK<\/a> ]<\/li>\n<li>S. Sudhakar, V. Sze, S. Karaman, &#8220;Data Centers on Wheels: Emissions from Computing Onboard Autonomous Vehicles,&#8221; <i>IEEE Micro, Special Issue on Environmentally Sustainable Computing<\/i>, Vol. 43, No. 1, pp. 29 &#8211; 39, January\/February 2023. [ paper <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/10\/2022_micro_carbonAV.pdf\">PDF<\/a> | slides <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/01\/2023_micro_carbonAV_slides.pdf\">PDF<\/a> | TEDx talk <a href=\"https:\/\/youtu.be\/v6mUTnXEjYw\">video<\/a> | Technical talk <a href=\"https:\/\/youtu.be\/l1z7hbIfrhg\">video<\/a> ] <strong><i>Highlighted in <a href=\"https:\/\/news.mit.edu\/2023\/autonomous-vehicles-carbon-emissions-0113\">MIT News<\/a> and <a href=\"https:\/\/www.washingtonpost.com\/technology\/2023\/01\/13\/self-driving-cars-greenhouse-gas-emissions\/\">The Washington Post<\/a> <\/i><\/strong><\/li>\n<\/ul>\n<h4>2022<\/h4>\n<ul>\n<li>Y. N. Wu, P. Tsai, A. Parashar, V. Sze, J. Emer, &#8220;Sparseloop: An Analytical Approach to Sparse Tensor Accelerator Modeling,&#8221; <i>ACM\/IEEE International Symposium on Microarchitecture (MICRO)<\/i>, October 2022. [ paper <a href=\"https:\/\/sparseloop.mit.edu\/documents\/2022-micro-sparseloop.pdf\">PDF<\/a> | video <a href=\"https:\/\/www.youtube.com\/watch?v=ptN_Swfc834\">LINK<\/a> | project website <a href=\"https:\/\/sparseloop.mit.edu\/\">LINK<\/a> | code <a href=\"https:\/\/github.com\/NVlabs\/timeloop\/releases\/tag\/v2.0\">github<\/a> ] <strong><i>MICRO 2022 Distinguished Artifact Award<\/i><\/strong><\/li>\n<li>S. Sudhakar, S. Karaman, V. Sze, &#8220;Carbon Emissions from Computing Onboard Autonomous Vehicles,&#8221; <i>ICRA 2022 Workshop on Robotics for Climate Change<\/i>, May 2022.<\/li>\n<li>P. Z. X. Li, S. Karaman, V. Sze, &#8220;Memory-Efficient Gaussian Fitting for Depth Images in Real Time,&#8221; <i>IEEE International Conference on Robotics and Automation (ICRA)<\/i>, May 2022. [ paper <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/03\/2022_icra_spgf.pdf\">PDF<\/a> | video <a href=\"https:\/\/youtu.be\/OfJjDTj7fCo\">LINK<\/a> ]<\/li>\n<li>S. Sudhakar, V. Sze, S. Karaman, &#8220;Uncertainty from Motion for DNN Monocular Depth Estimation,&#8221; <i>IEEE International Conference on Robotics and Automation (ICRA)<\/i>, May 2022. [ paper <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/03\/2022_icra_ufm.pdf\">PDF<\/a> | video <a href=\"https:\/\/youtu.be\/CNbR4E4w5d0\">LINK<\/a> ]<\/li>\n<li>H.-Y. Lai, G. Saavedra-Pena, C. G. Sodini, T. Heldt, V. Sze, &#8220;App-based saccade latency and directional error determination across the adult age spectrum,&#8221; <i>IEEE Transactions on Biomedical Engineering (TBME)<\/i>, Vol. 69, No. 2, pp. 1029 &#8211; 1039, February 2022. [ <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/02\/2022_tbme_lai.pdf\">PDF<\/a> ]<\/li>\n<\/ul>\n<h4>2021<\/h4>\n<ul>\n<li>Y.-L. Liao, S. Karaman, V. Sze, &#8220;Searching for Efficient Multi-Stage Vision Transformers,&#8221; <i>ICCV 2021 Workshop on Neural Architectures: Past, Present and Future<\/i>, October 2021. [ paper <a href=\"https:\/\/arxiv.org\/abs\/2109.00642\">arXiv<\/a> | code <a href=\"https:\/\/github.com\/yilunliao\/vit-search\">github<\/a> ]<\/li>\n<li>K. Gupta, P. Z. X. Li, S. Karaman, V. Sze, &#8220;Efficient Computation of Map-scale Continuous Mutual Information on Chip in Real Time,&#8221; <i>IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)<\/i>, September 2021. [ <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/09\/2021_iros_fcmihw.pdf\">PDF<\/a> ]<\/li>\n<li>T.-J. Yang, Y.-L. Liao, V. Sze, &#8220;NetAdaptV2: Efficient neural architecture search with fast super-network training and architecture optimization,&#8221; <i>IEEE Conference on Computer Vision and Pattern Recognition (CVPR)<\/i>, June 2021. [ paper <a href=\"https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/papers\/Yang_NetAdaptV2_Efficient_Neural_Architecture_Search_With_Fast_Super-Network_Training_and_CVPR_2021_paper.pdf\">PDF<\/a> | poster <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/02\/2021_cvpr_netadaptv2_poster.pdf\">PDF<\/a> | slides <a href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2022\/02\/2021_cvpr_netadaptv2_slides.pdf\">PDF<\/a> | project website <a class=\"2018pub2\" href=\"http:\/\/netadapt.mit.edu\/\">LINK<\/a> ]<\/li>\n<li>F. Wang, Y. N. Wu, M. Woicik, J. S. Emer, V. Sze, &#8220;Architecture-Level Energy Estimation for Heterogeneous Computing Systems,&#8221; <i>IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)<\/i>, March 2021. [ paper <a href=\"http:\/\/accelergy.mit.edu\/ispass2021\/hetergeneous_computing_abstract.pdf\">PDF<\/a> | code <a href=\"https:\/\/github.com\/Accelergy-Project\/accelergy-mcpat-plug-in\">github<\/a> ]<\/li>\n<li>Y. N. Wu, P.-A. Tsai, A. Parashar, V. Sze, J. S. Emer, &#8220;Sparseloop: An Analytical, Energy-Focused Design Space Exploration Methodology for Sparse Tensor Accelerators,&#8221; <i>IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)<\/i>, March 2021. [ paper <a href=\"http:\/\/accelergy.mit.edu\/ispass2021\/sparseloop_abstract.pdf\">PDF<\/a> | tutorial website <a href=\"http:\/\/accelergy.mit.edu\/sparse_tutorial.html\">LINK<\/a> ]<\/li>\n<li>L. Bernstein, A. Sludds, R. Hamerly, V. Sze, J. Emer, D. Englund, &#8220;Freely scalable and reconfigurable optical hardware for deep learning,&#8221; <i>Scientific Reports<\/i>, Vol. 11, No. 3144, February 2021. [ <a href=\"https:\/\/www.nature.com\/articles\/s41598-021-82543-3\">LINK<\/a> ]<\/li>\n<\/ul>\n<h4>2020<\/h4>\n<ul>\n<li>V. Sze, Y.-H. Chen, T.-Y. Yang, J. S. Emer, &#8220;How to Evaluate Deep Neural Network Processors: TOPS\/W (Alone) Considered Harmful,&#8221; <i>IEEE Solid-State Circuits Magazine<\/i>, Vol. 12, No. 3, pp. 28-41, Summer 2020. [ <a class=\"2020pub6 href=\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2020\/09\/ieee_mssc_summer2020.pdf\">PDF<\/a> ]<\/li>\n<li>Z. Zhang, T. Henderson, S. Karaman, V. Sze, &#8220;FSMI: Fast computation of Shannon Mutual Information for information-theoretic mapping,&#8221; <i>International Journal of Robotics Research (IJRR)<\/i>, Vol. 39, No. 9, pp. 1155-1177, August 2020. [ <a class=\"2020pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2020\/08\/2020_ijrr_fsmi.pdf\">PDF<\/a> ]<\/li>\n<li>J. Noraky, V. Sze, &#8220;Low Power Depth Estimation of Rigid Objects for Time-of-Flight Imaging,&#8221; <i>IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)<\/i>, Vol. 30, No. 6, pp. 1524-1534, June 2020. [ <a class=\"2020pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/03\/2019_tcsvt_tof.pdf\">PDF<\/a> ]<\/li>\n<li>S. Sudhakar, S. Karaman, V. Sze, &#8220;Balancing Actuation and Computing Energy in Motion Planning,&#8221; <i> IEEE International Conference on Robotics and Automation (ICRA)<\/i>, May 2020. [ <a class=\"2020pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2020\/03\/2020_icra_ceimp.pdf\">PDF<\/a> | video <a class=\"2020pub3\" href=\"https:\/\/youtu.be\/UxxnJbNMOOc\">LINK<\/a> ]<\/li>\n<li>T. Henderson, V. Sze, S. Karaman, &#8220;An Efficient and Continuous Approach to Information-Theoretic Exploration,&#8221; <i> IEEE International Conference on Robotics and Automation (ICRA)<\/i>, May 2020. [ paper <a class=\"2020pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2020\/03\/2020_icra_fcmi.pdf\">PDF<\/a> | video <a class=\"2020pub2\" href=\"https:\/\/youtu.be\/WYGlDQfI1yE\">LINK<\/a> ] <strong><i>Based on thesis that received First Place for the 2020 David Adler Memorial Thesis Award<\/i><\/strong><\/li>\n<li>Y. N. Wu, V. Sze, J. S. Emer, &#8220;An Architecture-Level Energy and Area Estimator for Processing-In-Memory Accelerator Designs,&#8221; <i> IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)<\/i>, April 2020. [ paper <a class=\"2020pub1\" href=\"http:\/\/accelergy.mit.edu\/accelergy_ISPASS.pdf\">PDF<\/a> | code <a href=\"https:\/\/github.com\/Accelergy-Project\/processing-in-memory-design\">github<\/a> ]<\/li>\n<li>H.-Y. Lai, G. Saavedra Pe\u00f1a, C. Sodini, V. Sze, T. Heldt, &#8220;Measuring Saccade Latency Using Smartphone Cameras,&#8221; <i> IEEE Journal of Biomedical and Health Informatics (JBHI)<\/i>, Vol. 24, No. 3, pp. 885-897, March 2020. [ <a class=\"2019pub3\" href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=8703178\">PDF<\/a> ]<\/li>\n<li>J. Noraky, V. Sze, &#8220;Depth Map Estimation of Dynamic Scenes Using Prior Depth Information,&#8221; arXiv, February 2020. [ paper <a href=\"https:\/\/arxiv.org\/abs\/2002.00297\">arXiv<\/a> ]<\/li>\n<\/ul>\n<h4>2019<\/h4>\n<ul>\n<li>T.-J. Yang, V. Sze, &#8220;Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators,&#8221; <i>IEEE International Electron Devices Meeting (IEDM)<\/i>, <i>Invited Paper<\/i>, December 2019. [ paper <a class=\"2019pub10\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/12\/2019_iedm_pim.pdf\">PDF<\/a> | slides <a class=\"2019pub10\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/12\/2019_iedm_pim_slides.pdf\">PDF<\/a> ]<\/li>\n<li>Y. N. Wu, J. S. Emer, V. Sze, &#8220;Accelergy: An Architecture-Level Energy Estimation Methodology for Accelerator Designs,&#8221; <i>International Conference on Computer Aided Design (ICCAD)<\/i>, November 2019. [ paper <a class=\"2019pub9\" href=\"http:\/\/accelergy.mit.edu\/paper.pdf\">PDF<\/a> | slides <a class=\"2019pub9\" href=\"http:\/\/accelergy.mit.edu\/slides.pdf\">PDF<\/a> | project website <a class=\"2019pub9\" href=\"http:\/\/accelergy.mit.edu\/\">LINK<\/a> | code <a class=\"2019pub9\" href=\"https:\/\/github.com\/nelliewu95\/accelergy\">github<\/a> ]<\/li>\n<li>J. Noraky, C. Mathy, A. Cheng, V. Sze, &#8220;Low Power Adaptive Time-Of-Flight Imaging For Multiple Rigid Objects,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, September 2019. [ <a class=\"2019pub8\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/05\/2019_icip_tof.pdf\">PDF<\/a> ]<\/li>\n<li>P. Z. X. Li*, Z. Zhang*, S. Karaman, V. Sze, &#8220;High-throughput Computation of Shannon Mutual Information on Chip,&#8221; <i>Robotics: Science and Systems (RSS)<\/i>, June 2019. [ paper <a class=\"2019pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/05\/2019_rss_fsmi_hardware.pdf\">PDF<\/a> | poster <a class=\"2019pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/06\/2019_rss_fsmi_hardware_poster.pdf\">PDF<\/a> | slides <a class=\"2019pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/06\/2019_rss_fsmi_hardware_slides.pdf\">PDF<\/a> | video <a class=\"2019pub7\" href=\"https:\/\/youtu.be\/mGQCkhOh6u8?t=9962\">LINK<\/a> | supplementary material <a class=\"2019pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/05\/2019_rss_fsmi_hardware_supplementary.pdf\">PDF<\/a> ] <strong><i><a href=\"https:\/\/src.acm.org\/binaries\/content\/assets\/src\/2020\/peter-zhi-xuan-li.pdf\">Extension of this work<\/a> received First Place at the <a href=\"https:\/\/www.acm.org\/media-center\/2020\/june\/src-2020-grand-finals\">2020 ACM Student Research Competition Grand Finals<\/a><\/i><\/strong><\/li>\n<li>Y.-H. Chen, T.-J Yang, J. Emer, V. Sze, &#8220;Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices,&#8221; <i>IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS)<\/i>, Vol. 9, No. 2, pp. 292-308, June 2019. [ paper <a class=\"2018pub6\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/04\/2019_jetcas_eyerissv2.pdf\">PDF<\/a> | extended version <a class=\"2018pub6\" href=\"https:\/\/arxiv.org\/abs\/1807.07928\">arXiv<\/a> ]<\/li>\n<li>Z. Zhang, T. Henderson, V. Sze, S. Karaman, &#8220;FSMI: Fast computation of Shannon Mutual Information for information-theoretic mapping,&#8221; <i>IEEE International Conference on Robotics and Automation (ICRA)<\/i>, May 2019. [ paper <a class=\"2019pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/08\/2019_icra_fsmi.pdf\">PDF<\/a> | poster <a class=\"2019pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/05\/2019_icra_fsmi_poster.pdf\">PDF<\/a> | summary <a class=\"2019pub2\" href=\"https:\/\/youtu.be\/N7mi9uXKrP4\">video<\/a> | extended preprint <a class=\"2019pub2\" href=\"http:\/\/arxiv.org\/abs\/1905.02238 \">arXiv<\/a> ]<\/li>\n<li>D. Wofk*, F. Ma*, T.-J. Yang, S. Karaman, V. Sze, &#8220;FastDepth: Fast Monocular Depth Estimation on Embedded Systems,&#8221; <i>IEEE International Conference on Robotics and Automation (ICRA)<\/i>, May 2019. [ paper <a class=\"2019pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/03\/2019_icra_fastdepth.pdf\">PDF<\/a> | poster <a class=\"2019pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2019\/05\/2019_icra_fastdepth_poster.pdf\">PDF<\/a> | project website <a class=\"2019pub1\" href=\"http:\/\/fastdepth.mit.edu\/\">LINK<\/a> | summary <a class=\"2019pub1\" href=\"https:\/\/youtu.be\/gRqrYJWyXyI\">video<\/a> | code <a class=\"2019pub1\" href=\"https:\/\/github.com\/dwofk\/fast-depth\">github<\/a> ] <i><strong>Received SuperUROP Award<\/strong><\/i><\/li>\n<li>A. Suleiman, Z. Zhang, L. Carlone, S. Karaman, V. Sze, &#8220;Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones,&#8221; <i>IEEE Journal of Solid-State Circuits (JSSC), VLSI Symposia Special Issue<\/i>, Vol. 54, No. 4, pp. 1106-1119, April 2019. [ paper <a class=\"2018pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/12\/2019_jssc_navion.pdf\">PDF<\/a> | project website <a class=\"2018pub4\" href=\"http:\/\/navion.mit.edu\">LINK<\/a> ]<\/li>\n<li>T.-J. Yang, M. D. Collins, Y. Zhu, J.-J. Hwang, T. Liu, X. Zhang, V. Sze, G. Papandreou, L.-C. Chen, &#8220;DeeperLab: Single-Shot Image Parser,&#8221; arXiv, February 2019. [ paper <a class=\"2019pub3\" href=\"https:\/\/arxiv.org\/abs\/1902.05093\">arXiv<\/a> | project website <a class=\"2019pub3\" href=\"http:\/\/deeperlab.mit.edu\/\">LINK<\/a> ]<\/li>\n<\/ul>\n<h4>2018<\/h4>\n<ul>\n<li>J. Noraky, V. Sze, &#8220;Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, October 2018. [ paper <a class=\"2018pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/06\/2018_icip_non_rigid_depth.pdf\">PDF<\/a> | poster <a class=\"2018pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/10\/2018_icip_tof_poster.pdf\">PDF<\/a> ]<\/li>\n<li>H.-Y. Lai, G. Saavedra Pe\u00f1a, C. Sodini, T. Heldt, V. Sze, &#8220;Enabling Saccade Latency Measurements with Consumer-Grade Cameras,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, October 2018. [ paper <a class=\"2018pub9\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/10\/2018_icip_saccades.pdf\">PDF<\/a> | poster <a class=\"2018pub9\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/10\/2018_icip_saccades_poster.pdf\">PDF<\/a> ]<\/li>\n<li>T.-J. Yang, A. Howard, B. Chen, X. Zhang, A. Go, M. Sandler, V. Sze, H. Adam, &#8220;NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications,&#8221; <i>European Conference on Computer Vision (ECCV)<\/i>, September 2018. [ paper <a class=\"2018pub2\" href=\"https:\/\/arxiv.org\/abs\/1804.03230\">arXiv<\/a> | poster <a class=\"2018pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/09\/2018_eccv_netadapt_yang_poster.pdf\">PDF<\/a> | project website <a class=\"2018pub2\" href=\"http:\/\/netadapt.mit.edu\/\">LINK<\/a> | code <a class=\"2018pub2\" href=\"https:\/\/github.com\/denru01\/netadapt\">github<\/a> ]<\/li>\n<li>M. Tikekar, V. Sze, A. P. Chandrakasan, \u201cA Fully-Integrated Energy-Efficient H.265\/HEVC Decoder With eDRAM for Wearable Devices,\u201d <i>IEEE Journal of Solid-State Circuits (JSSC)<\/i>, Vol. 53, No. 8, pp. 2368-2377, August 2018. [ <a class=\"2018pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/05\/2018_jssc_wearable_hevc.pdf\">PDF<\/a> ]<\/li>\n<li>G. Saavedra Pe\u00f1a, H.-Y. Lai, V. Sze, T. Heldt, &#8220;Determination of saccade latency distributions using video recordings from consumer-grade devices,&#8221; <i>IEEE International Engineering in Medicine and Biology Conference (EMBC)<\/i>, July 2018. [ paper <a class=\"2018pub10\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/07\/2018_embc_saavedra.pdf\">PDF<\/a> | poster <a class=\"2018pub10\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/07\/2018_embc_saavedra_poster.pdf\">PDF<\/a> ]<\/li>\n<li>A. Suleiman, Z. Zhang, L. Carlone, S. Karaman, V. Sze, \u201cNavion: A Fully Integrated Energy-Efficient Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones,\u201d\u00a0<i>IEEE Symposium on VLSI Circuits (VLSI-Circuits)<\/i>, June 2018.\u00a0[ paper <a class=\"2018pub4\" href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2018_vlsi_navion.pdf\">PDF<\/a> | slides <a href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2018_vlsi_navion_slides.pdf\">PDF<\/a> | poster <a href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2018_vlsi_navion_poster.pdf\">PDF<\/a> | project website <a class=\"2018pub4\" href=\"http:\/\/navion.mit.edu\">LINK<\/a> ]\u00a0<strong><i>Featured as a\u00a0<a href=\"http:\/\/vlsisymposium.org\/wp-content\/uploads\/2018\/05\/NEW-2018-VLSI-tip-sheet-combined-FINAL-4.17.18.pdf\">technical highlight<\/a>\u00a0at the conference, highlighted in <a href=\"http:\/\/news.mit.edu\/2018\/novel-chip-upgrade-helps-miniature-drones-navigate-0620\">MIT News<\/a>, and received Best Student Paper Award<\/i><\/strong><\/li>\n<li>Y.-H. Chen*, T.-J. Yang*, J. Emer, V. Sze, &#8220;Understanding the Limitations of Existing Energy-Efficient Design Approaches for Deep Neural Networks,&#8221; <i>SysML Conference<\/i>, February 2018. [ paper <a class=\"2018pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/02\/2018_SysML_final.pdf\">PDF<\/a> | talk <a class=\"2018pub1\" href=\"https:\/\/www.youtube.com\/watch?v=XCdy5egmvaU\">video<\/a> ]<strong><i> Selected for Oral Presentation<\/i><\/strong><\/li>\n<\/ul>\n<h4>2017<\/h4>\n<ul>\n<li>V. Sze, Y.-H. Chen, T.-J. Yang, J. Emer, &#8220;Efficient Processing of Deep Neural Networks: A Tutorial and Survey,&#8221; <i>Proceedings of the IEEE<\/i>, vol. 105, no. 12, pp. 2295-2329, December 2017. [ <a class=\"2017pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/11\/2017_pieee_dnn.pdf\">PDF<\/a> | earlier version <a class=\"2017pub4\" href=\"http:\/\/arxiv.org\/abs\/1703.09039\">arXiv<\/a> ] <strong><i>Cover Article in <a href=\"http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=8114726\">Proceedings of the IEEE<\/a><\/i><\/strong><\/li>\n<li>V. Sze, &#8220;Designing Hardware for Machine Learning: The Important Role Played by Circuit Designers,&#8221; <i>IEEE Solid-State Circuits Magazine<\/i>, vol. 9, no. 4, pp. 46-54, Fall 2017. [ <a href=\"http:\/\/ieeexplore.ieee.org\/document\/8110880\/\">LINK<\/a> ]<\/li>\n<li>T.-J. Yang, Y.-H. Chen, J. Emer, V. Sze, &#8220;A Method to Estimate the Energy Consumption of Deep Neural Networks,&#8221; <i>Asilomar Conference on Signals, Systems and Computers<\/i>, <i>Invited Paper<\/i>, October 2017. [ paper <a class=\"2017pub9\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/12\/2017_asilomar_tool.pdf\">PDF<\/a> | slides <a class=\"2017pub9\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/12\/2017_asilomar_tool_slides.pdf\">PDF<\/a> ]<\/li>\n<li>J. Noraky, V. Sze, &#8220;Low Power Depth Estimation for Time-of-Flight Imaging,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, September 2017. [ paper <a class=\"2017pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/06\/2017_icip_tof.pdf\">PDF<\/a> | poster <a class=\"2017pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/09\/2017_icip_tof_poster.pdf\">PDF<\/a> ]<\/li>\n<li>T.-J. Yang, Y.-H. Chen, V. Sze, &#8220;Designing Energy-Efficient Convolutional Neural Networks<br \/>\nusing Energy-Aware Pruning,&#8221; <i>IEEE Conference on Computer Vision and Pattern Recognition (CVPR)<\/i>, July 2017. [ paper <a class=\"2016pub5\" href=\"http:\/\/arxiv.org\/abs\/1611.05128\">arXiv<\/a> | poster <a class=\"2016pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/07\/2017_cvpr_poster.pdf\">PDF<\/a> | DNN energy estimation tool <a href=\"http:\/\/energyestimation.mit.edu\">LINK<\/a> | DNN models <a class=\"2016pub5\" href=\"http:\/\/eyeriss.mit.edu\/energy.html\">LINK<\/a> ] <strong><i>Highlighted in <a href=\"http:\/\/news.mit.edu\/2017\/bringing-neural-networks-cellphones-0718\">MIT News<\/a><\/i><\/strong><\/li>\n<li>Z. Zhang, V. Sze, &#8220;FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos,&#8221; <i>CVPR Workshop on New Trends in Image Restoration and Enhancement<\/i>, July 2017. [ paper <a class=\"2016pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/05\/2017_cvprw_FAST.pdf\">PDF<\/a> | slides <a class=\"2017pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/07\/2017_ntire_fast_slides.pdf\">PDF<\/a> | poster <a class=\"2017pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/07\/2017_ntire_fast_poster.pdf\">PDF<\/a> | code <a class=\"2017pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2018\/08\/FAST_code_release_r1.zip\">ZIP<\/a> | earlier version <a class=\"2016pub1\" href=\"https:\/\/arxiv.org\/abs\/1603.08968\">arXiv<\/a> | project website <a href=\"http:\/\/www.mit.edu\/~sze\/fast.html\">LINK<\/a> ]<\/li>\n<li>Z. Zhang*, A. Suleiman*, L. Carlone, V. Sze, S. Karaman, &#8220;Visual-Inertial Odometry on Chip: An Algorithm-and-Hardware Co-design Approach,&#8221; <i>Robotics: Science and Systems (RSS)<\/i>, July 2017. [ paper <a class=\"2017pub6\" href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2017_rss_navion.pdf\">PDF<\/a> | slides <a class=\"2017pub6\" href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2017_rss_navion_slides.pdf\">PDF<\/a> | poster <a class=\"2017pub6\" href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2017_rss_navion_poster.pdf\">PDF<\/a> | supplementary material <a class=\"2017pub6\" href=\"http:\/\/web.mit.edu\/sze\/www\/navion\/2017_rss_navion_supplementary.pdf\">PDF<\/a> | project website <a class=\"2017pub6\" href=\"http:\/\/navion.mit.edu\">LINK<\/a> ] <strong><i>Highlighted in <a href=\"http:\/\/news.mit.edu\/2017\/miniaturizing-brain-smart-drones-0712\">MIT News<\/a><\/i><\/strong><\/li>\n<li>M. Tikekar, V. Sze, A. Chandrakasan, &#8220;A Fully-Integrated Energy-Efficient H.265\/HEVC Decoder with eDRAM for Wearable Devices,&#8221; <i>IEEE Symposium on VLSI Circuits (VLSI-Circuits)<\/i>, June 2017. [ paper <a class=\"2017pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/06\/2017_vlsi_hevc.pdf\">PDF<\/a> | slides <a class=\"2017pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/06\/2017_vlsi_hevc_slides.pdf\">PDF<\/a> ]<\/li>\n<li>Y.-H. Chen, J. Emer, V. Sze, &#8220;Using Dataflow to Optimize Energy Efficiency of Deep Neural Network Accelerators,&#8221; <i>IEEE Micro&#8217;s Top Picks from the Computer Architecture Conferences<\/i>, Vol. 37, No. 3, pp. 12-21, May\/June 2017. [ <a class=\"2017pub8\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/06\/2017_micro_toppicks.pdf\">PDF<\/a> ] <b><i>IEEE MICRO Top 25 Most Downloaded (June 2017 &#8211; May 2018)<\/i><\/b><\/li>\n<li>A. Suleiman*, Y.-H. Chen*, J. Emer, V. Sze, &#8220;Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision,&#8221; <i>IEEE International Symposium of Circuits and Systems (ISCAS)<\/i>, <i>Invited Paper<\/i>, May 2017. [ paper <a class=\"2017pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/03\/2017_iscas_HOG_CNN.pdf\">PDF<\/a> | slides <a class=\"2017pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/05\/2017_iscas_slides.pdf\">PDF<\/a> | talk <a class=\"2017pub3\" href=\"https:\/\/www.youtube.com\/watch?v=oXmlUxpC14Q&amp;feature=youtu.be\">video<\/a> ]<\/li>\n<li>V. Sze, Y.-H. Chen, J. Emer, A. Suleiman, Z. Zhang, &#8220;Hardware for Machine Learning: Challenges and Opportunities,&#8221; <i>IEEE Custom Integrated Circuits Conference (CICC)<\/i>, <i>Invited Paper<\/i>, May 2017. [ paper <a class=\"2016pub6\" href=\"http:\/\/arxiv.org\/abs\/1612.07625\">arXiv<\/a> | slides <a class=\"2016pub6\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/05\/2017_cicc_slides.pdf\">PDF<\/a> ] <strong><i>Received Outstanding Invited Paper Award<\/i><\/strong><\/li>\n<li>A. Suleiman, Z. Zhang, V. Sze, &#8220;A 58.6mW 30fps Real-Time Programmable Multi-Object Detection Accelerator with Deformable Parts Models on Full HD 1920&#215;1080 Videos,&#8221; <i>IEEE Journal of Solid-State Circuits (JSSC)<\/i>, Vol. 52, No. 3, pp. 844-855, March 2017. [ <a class=\"2017pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2017\/01\/2017_jssc_dpm.pdf\">PDF<\/a> ]<\/li>\n<li>Y.-H. Chen, T. Krishna, J. Emer, V. Sze, &#8220;Eyeriss:\u00a0An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks,&#8221; <i>IEEE Journal of Solid-State Circuits (JSSC), ISSCC Special Issue<\/i>, Vol. 52, No. 1, pp. 127-138, January 2017. [ paper <a class=\"2017pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/11\/eyeriss_jssc_2017.pdf\">PDF<\/a> | project website <a class=\"2016pub4\" href=\"http:\/\/eyeriss.mit.edu\">LINK<\/a> ]\u00a0<b><i>Top 5 most cited JSSC paper of all time<\/i><\/b><\/li>\n<\/ul>\n<h4>2016<\/h4>\n<ul>\n<li>Y.-H. Chen, J. Emer, V. Sze, &#8220;Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks,&#8221; <i>International Symposium on Computer Architecture (ISCA)<\/i>,\u00a0pp. 367-379, June 2016. [ paper <a class=\"2016pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/04\/eyeriss_isca_2016.pdf\">PDF<\/a> | slides <a class=\"2016pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/06\/eyeriss_isca_2016_slides.pdf\">PDF<\/a> ] <i><b>Selected for IEEE Micro\u2019s Top Picks special issue on &#8220;most significant papers in computer architecture based on novelty and long-term impact&#8221; from 2016<\/b><\/i><\/li>\n<li>A. Suleiman, Z. Zhang, V. Sze, &#8220;A 58.6mW Real-time Programmable Object Detection with Multi-Scale Multi-Object Support Using Deformable Parts Models on 1920&#215;1080 Video at 30fps,&#8221; <i>IEEE Symposium on VLSI Circuits (VLSI-Circuits)<\/i>, pp. 184-185, June 2016. [ paper <a class=\"2016pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/06\/dpm_vlsi_2016.pdf\">PDF<\/a> | slides <a class=\"2016pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/06\/dpm_vlsi_2016_slides.pdf\">PDF<\/a> ]<\/li>\n<li>Y.-H. Chen, T. Krishna, J. Emer, V. Sze, &#8220;Eyeriss:\u00a0An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks,&#8221; <i>IEEE International Conference on Solid-State Circuits (ISSCC)<\/i>, pp. 262-264, February 2016.\u00a0[ paper <a class=\"2016pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/02\/eyeriss_isscc_2016.pdf\">PDF<\/a> | slides <a class=\"2016pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/02\/eyeriss_isscc_2016_slides.pdf\">PDF<\/a> | poster <a class=\"2016pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/04\/eyeriss_isscc_2016_poster.pdf\">PDF<\/a> | demo <a class=\"2016pub4\" href=\"https:\/\/vimeo.com\/154012013\">video<\/a>\u00a0| project website <a class=\"2016pub4\" href=\"http:\/\/eyeriss.mit.edu\">LINK<\/a> ] <strong><i>Highlighted in <a class=\"2016pub4\" href=\"http:\/\/www.eetimes.com\/document.asp?doc_id=1328272&amp;page_number=3\">EETimes<\/a> and <a class=\"2016pub4\" href=\"http:\/\/news.mit.edu\/2016\/neural-chip-artificial-intelligence-mobile-devices-0203\">MIT News<\/a>, and Top 3 most cited ISSCC paper of all time<\/i><\/strong><\/li>\n<\/ul>\n<h4>2015<\/h4>\n<ul>\n<li>A. Suleiman, V. Sze, &#8220;An Energy-efficient Hardware Implementation of HOG-based Object Detection at 1080HD 60 fps with Multi-scale Support,&#8221; <i>Journal of Signal Processing Systems<\/i>, <em>SiPS Special Issue<\/em>,\u00a0December 2015. [ <a class=\"2015pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/10\/suleiman_jsps_2015.pdf\">PDF<\/a> ]<\/li>\n<li>Z. Zhang, V. Sze, &#8220;Rotate Intra Block Copy for Still Image Coding,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, September 2015. [ paper <a class=\"2015pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/12\/zhang_icip_2015.pdf\">PDF<\/a> | poster <a class=\"2015pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/09\/zhang_icip_2015_poster.pdf\">PDF<\/a> ]<\/li>\n<li>Y.-H. Chen, V. Sze, &#8220;A Deeply Pipelined CABAC Decoder for HEVC Supporting Level 6.2 High-Tier Applications,&#8221;\u00a0<i>IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)<\/i>, Vol. 25, No. 5, pp. 856-868, May 2015. [ <a class=\"2015pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/chen_tcsvt_2014.pdf\">PDF<\/a>\u00a0]<\/li>\n<\/ul>\n<h4>2014<\/h4>\n<ul>\n<li>A. Suleiman, V. Sze, &#8220;<span style=\"color: #222222;\">Energy-Efficient HOG-based Object Detection at 1080HD 60 fps with Multi-Scale Support<\/span>,&#8221; <i>IEEE International Workshop on Signal Processing Systems\u00a0(SiPS)<\/i>, pp. 256-261,\u00a0October 2014. [ paper <a class=\"2014pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/10\/suleiman_sips_2014.pdf\">PDF<\/a> | slides <a class=\"2014pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/09\/suleiman_sips_2014_slides.pdf\">PDF<\/a> ]<\/li>\n<li>Y.-H. Chen, V. Sze, &#8220;A 2014 Mbin\/s Deeply Pipelined CABAC Decoder For HEVC,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>,\u00a0pp. 2110-2114, October 2014. [ paper <a class=\"2014pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/chen_icip_2014.pdf\">PDF<\/a> | slides <a class=\"2014pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/08\/chen_icip_2014_slides.pdf\">PDF<\/a> ]<\/li>\n<li>M. Tikekar, C.-T. Huang, V. Sze, A. Chandrakasan, &#8220;Energy and Area-Efficient Hardware Implementation of HEVC Inverse Transform and Dequantization,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>,\u00a0pp. 2100-2104, October 2014. [ paper <a class=\"2014pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/tikekar_icip_2014.pdf\">PDF<\/a> | slides <a class=\"2014pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2015\/08\/tikekar_icip_2014_slides.pdf\">PDF<\/a> ] <em><strong>Top 10% Paper Recognition at ICIP<\/strong><\/em><\/li>\n<li>M. Tikekar, C.-T. Huang, C. Juvekar, V. Sze, A. P. Chandrakasan, \u201cA 249 MPixel\/s HEVC Video-Decoder Chip for 4K Ultra HD Applications,\u201d <i>IEEE Journal of Solid-State Circuits (JSSC), ISSCC Special Issue<\/i>, Vol. 49, No. 1, pp. 61-72, January 2014. [ <a class=\"2014pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/tikekar_jssc_2014.pdf\">PDF<\/a>\u00a0]<\/li>\n<\/ul>\n<h4>2013<\/h4>\n<ul>\n<li>M. E. Sinangil, V. Sze, M. Zhou, A. P. Chandrakasan, &#8220;Cost and Coding Efficient Motion Estimation Design Considerations for High Efficiency Video Coding (HEVC) Standard,&#8221; <i>IEEE Journal of Selected Topics in Signal Processing<\/i>, Vol. 7, No.6, pp. 1017-1028, December 2013. [ <a class=\"2013pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sinangil_jstsp_2013.pdf\">PDF<\/a> ]\u00a0<b><i>J-STSP Top 25 Most Downloaded (Oct 2013 &#8211; March 2014)<\/i><\/b><\/li>\n<li>M. Budagavi, A. Fuldseth, G. Bjontegaard, V. Sze, M. Sadafale, &#8220;Core Transform Design in the High Efficiency Video Coding (HEVC) Standard,&#8221; <i>IEEE Journal of Selected Topics in Signal Processing<\/i>, Vol.7, No. 6, pp. 1029-1041, December 2013. [ <a class=\"2013pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/budagavi_jstsp_2013.pdf\">PDF<\/a> ]\u00a0<b><i>J-STSP Top 25 Most Downloaded (Aug 2013 &#8211; Aug\u00a02014)<\/i><\/b><\/li>\n<li>V. Sze, M. Budagavi, &#8220;A Comparison of CABAC Throughput for HEVC\/H.265 vs. AVC\/H.264,&#8221; <i>IEEE Workshop on Signal Processing Systems (SiPS)<\/i>, pp. 165-170, October 2013. [ <a class=\"2013pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_sips_2013.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>C.-T. Huang, M. Tikekar, C. Juvekar, V. Sze, A. P. Chandrakasan, &#8220;A 249Mpixels\/s HEVC Video Decoder Chip for Quad Full HD Applications,&#8221; <i>IEEE International Conference on Solid-State Circuits (ISSCC)<\/i>, pp. 162-163, February 2013. [ <a class=\"2013pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/huang_isscc_2013.pdf\">PDF<\/a>\u00a0] <strong><i>Highlighted in <a href=\"http:\/\/news.mit.edu\/2013\/mit-researchers-build-quad-hd-tv-chip-0220\">MIT News<\/a><\/i><\/strong><\/li>\n<\/ul>\n<h4>2012<\/h4>\n<ul>\n<li>V. Sze, M. Budagavi, &#8220;High Throughput CABAC Entropy Coding in HEVC,&#8221;\u00a0<i>IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)<\/i>, Vol. 22, No. 12, pp. 1778-1791, December 2012. [ <a class=\"2012pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_tcsvt_2012.pdf\">PDF<\/a>\u00a0]\u00a0<b><i>TCSVT Top 25 Most Downloaded (June 2013, Aug 2013, Nov 2013, April 2014)<\/i><\/b><\/li>\n<li>M. E. Sinangil, V. Sze, M. Zhou, A. P. Chandrakasan, &#8220;Memory cost vs. Coding efficiency trade-offs for HEVC motion estimation engine,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, pp. 1533-1536, September 2012. [ <a class=\"2012pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sinangil_icip_2012_mem.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>M. E. Sinangil, V. Sze, M. Zhou, A. P. Chandrakasan, &#8220;Hardware-aware motion estimation search algorithm development for High-Efficiency Video Coding (HEVC) standard,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, pp. 1529-1532, September 2012. [ <a class=\"2012pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sinangil_icip_2012_hw.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>M. Budagavi, V. Sze, &#8220;Unified forward+inverse transform architecture for HEVC,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, pp. 209-212,\u00a0September 2012. [ <a class=\"2012pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/budagavi_icip_2012.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>M. Zhou, V. Sze, M. Budagavi, &#8220;Parallel Tools in HEVC for High-Throughput Processing,&#8221; <i>SPIE Optical Engineering + Applications<\/i>, Applications of Image Processing XXXV, August 2012. [ <a class=\"2012pub5\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/zhou_spie_2012.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>V. Sze, M. Budagavi, &#8220;Parallelization of Transform Coefficient Coding for HEVC,&#8221; <i>IEEE Picture Coding Symposium (PCS)<\/i>, pp. 509 \u2013 512, May 2012. [ <a class=\"2012pub6\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_pcs_2012.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>V. Sze, A. P. Chandrakasan, &#8220;Joint Algorithm-Architecture Optimization of CABAC,&#8221;\u00a0<i>Journal of Signal Processing Systems<\/i>, \u00a0<em>ICASSP-DISPS Track S<\/em><i>pecial Issue,\u00a0<\/i>Vol. 69, Issue 3, pp. 239-252, May\u00a02012. [ <a class=\"2012pub7\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_jsps_2012.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>V. Sze, A. P. Chandrakasan, &#8220;A Highly Parallel and Scalable CABAC Decoder for Next-Generation Video Coding,&#8221;\u00a0<i>IEEE Journal of Solid-State Circuits (JSSC), ISSCC Special Issue<\/i>, Vol. 47, No. 1, pp. 8-22, January 2012. [\u00a0<a class=\"2012pub8\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_jssc_2012.pdf\">PDF<\/a>\u00a0]<\/li>\n<\/ul>\n<h4>2011<\/h4>\n<ul>\n<li>M. Budagavi, V. Sze, M. Zhou, &#8220;HEVC ALF decode complexity analysis and reduction,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, pp. 745-748, September 2011. [ <a class=\"2011pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/budagavi_icip_2011.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>V. Sze, A. P. Chandrakasan, &#8220;Joint Algorithm-Architecture Optimization of CABAC to Increase Speed and Reduce Area Cost,&#8221; <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)<\/i>, pp. 1577\u20131580, May 2011. [ <a class=\"2011pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_icassp_2011.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>V. Sze, A. P. Chandrakasan, &#8220;A Highly Parallel and Scalable CABAC Decoder for Next-Generation Video Coding,&#8221; <i>IEEE International Conference on Solid-State Circuits (ISSCC)<\/i>, pp. 126-127, February 2011. [ paper <a class=\"2011pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/sze_isscc_2011.pdf\">PDF<\/a>\u00a0| slides <a class=\"2011pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2016\/06\/ISSCC2011_V07_02.pdf\">PDF<\/a> ]\u00a0<strong><i>Highlighted in <a href=\"http:\/\/www.eetimes.com\/electronics-news\/4213409\/ISSCC--Algorithm-paves-path-to-better-video\">EEtimes<\/a><\/i><\/strong><\/li>\n<\/ul>\n<h4>2010<\/h4>\n<ul>\n<li>A. P. Chandrakasan, D. C. Daly, D. F. Finchelstein, J. Kwong, Y. K. Ramadass, M. E. Sinangil, V. Sze, N. Verma, &#8220;Technologies for Ultra Dynamic Voltage Scaling,&#8221;\u00a0<i>Proceedings of the IEEE<\/i>, Vol. 98, No. 2, pp. 191-214, February 2010. [\u00a0<a class=\"2010pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2014\/10\/chandrakasan_pieee_2010.pdf\">PDF<\/a>\u00a0]<\/li>\n<\/ul>\n<h4>2009<\/h4>\n<ul>\n<li>V. Sze, D. F. Finchelstein, M. E. Sinangil, A. P. Chandrakasan, &#8220;A 0.7-V 1.8-mW H.264\/AVC 720p Video Decoder,&#8221;\u00a0<i>IEEE Journal of Solid-State Circuits (JSSC), A-SSCC Special Issue\u00a0<\/i>, Vol. 44, No. 11, pp. 2943-2956, November 2009. [\u00a0<a class=\"2009pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/2009_sze_jssc_nov.pdf\">PDF<\/a>\u00a0]<\/li>\n<li>D. F. Finchelstein, V. Sze, A. P. Chandrakasan, &#8220;Multi-Core Processing and Efficient On-Chip Caching for H.264 and Future Video Decoders,&#8221;\u00a0<i>IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)<\/i>, Vol. 19, No. 11, pp. 1704-1713, November 2009. [\u00a0<a class=\"2009pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/2009_finchelstein_tcsvt_nov.pdf\">PDF<\/a>\u00a0]\u00a0<strong><i>Nominated for Best Paper Award<\/i><\/strong><\/li>\n<li>V. Sze, A. P. Chandrakasan, &#8220;A High Throughput CABAC Algorithm Using Syntax Element Partitioning,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, pp. 773-776, November 2009. [\u00a0paper <a class=\"2009pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/sze_icip2009_paper.pdf\">PDF<\/a> | slides <a class=\"2009pub3\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/sze_icip2009_slides.pdf\">PDF<\/a> ]<\/li>\n<li>A. P. Chandrakasan, F. S. Lee, D. D. Wentzloff, V. Sze, B. P. Ginsburg, P. P. Mercier, D. C. Daly, R. Blazquez, &#8220;Low-Power Impulse UWB Architectures and Circuits,&#8221;\u00a0<i>Proceedings of the IEEE<\/i>, Vol. 97, No. 2, pp. 332-352, February 2009. [\u00a0<a class=\"2009pub4\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/2009_chandrakasan_ieee_feb.pdf\">PDF<\/a>\u00a0]<\/li>\n<\/ul>\n<h4>2008<\/h4>\n<ul>\n<li>D. F. Finchelstein, V. Sze, M. E. Sinangil, Y. Koken, A. P. Chandrakasan, &#8220;A Low-Power 0.7-V H.264 720p Video Decoder,&#8221; <i>IEEE Asian Solid-State Circuits Conference (A-SSCC)<\/i>, pp. 173-176, November 2008. [\u00a0paper <a class=\"2008pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/dfinchel_asscc2008_paper.pdf\">PDF<\/a> | slides <a class=\"2008pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/dfinchel_asscc2008_slides.pdf\">PDF<\/a> ] <strong><i>Student Design Contest Winner and selected as one of 9 <a href=\"http:\/\/www.asscc.org\/2008\/program.html\">noteworthy technical papers<\/a> at the conference<\/i><\/strong><\/li>\n<li>V. Sze, M. Budagavi, A. P. Chandrakasan, M. Zhou, &#8220;Parallel CABAC for Low Power Video Coding,&#8221; <i>IEEE International Conference on Image Processing (ICIP)<\/i>, pp. 2096-2099, October 2008. [\u00a0paper <a class=\"2008pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/vsze_icip2008_paper.pdf\">PDF<\/a> | poster <a class=\"2008pub2\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/vsze_icip2008_poster.pdf\">PDF<\/a> ]<\/li>\n<\/ul>\n<h4>2007<\/h4>\n<ul>\n<li>V. Sze, A. P. Chandrakasan, &#8220;A 0.4-V UWB Baseband Processor,&#8221; <i>IEEE International Symposium Low Power Electronics and Design (ISLPED)<\/i>, pp. 262-267, August 2007. [\u00a0paper <a class=\"2007pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/sze_islped2007_paper.pdf\">PDF<\/a> | slides <a class=\"2007pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/sze_islped2007_slides.pdf\">PDF<\/a> ]\u00a0<strong><i>Finalist for Best Paper Award<\/i><\/strong><\/li>\n<li>B. P. Ginsburg, V. Sze, A. P. Chandrakasan, &#8220;A Parallel Energy Efficient 100Mbps Ultra-Wideband Radio Baseband,&#8221; <i>Government Microcircuit Applications &amp; Critical Technology Conference (GOMACTech)<\/i>, pp. 75-78, March 2007.<\/li>\n<\/ul>\n<h4>2006<\/h4>\n<ul>\n<li>V. Sze, R. Blazquez, M. Bhardwaj, A. Chandrakasan, &#8220;An Energy Efficient Sub-Threshold Baseband Processor Architecture for Pulsed Ultra-Wideband Communications,&#8221; <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)<\/i>, pp. (III) 908-911, May 2006. [\u00a0paper <a class=\"2006_pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/sze_icassp2006_paper.pdf\">PDF<\/a> | slides <a class=\"2006pub1\" href=\"https:\/\/eems.mit.edu\/wp-content\/uploads\/2023\/08\/sze_icassp2006_slides.pdf\">PDF<\/a> ]<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>This material is presented to ensure the timely dissemination of scholarly and technical work. All persons copying this material are expected to adhere to the terms and constraints invoked by the copyright holder. In most cases, these works may not be reposted without the explicit permission of the copyright holder. * Indicates authors contributed equally [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":3,"comment_status":"open","ping_status":"open","template":"","meta":{"_et_pb_use_builder":"off","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"class_list":["post-11","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/pages\/11","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/comments?post=11"}],"version-history":[{"count":9,"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/pages\/11\/revisions"}],"predecessor-version":[{"id":3320,"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/pages\/11\/revisions\/3320"}],"wp:attachment":[{"href":"https:\/\/eems.mit.edu\/dev_site\/wp-json\/wp\/v2\/media?parent=11"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}