OverSeer: Efficient DNN Execution on Heterogeneous Devices: Rohan Mukherjee (Rice University); Zhi Chen (AWS); Vin Sharma (AWS); Animesh Jain (AWS)
Lessons learnt from shipping Intelligent Feeds to Microsoft Teams: Mohammad Luqman (Microsoft); Juhi Dua (Microsoft); Shivangi Dhakad (Microsoft); Anurag Mishra (Microsoft IDC); Pooja Aggarwal (Microsoft)
PRmalloc: Leveraging Predictability for DeepLearning Memory Allocation: Wencong Xiao (Alibaba Group); Shiru Ren (Alibaba Group); Tongxuan Liu (Alibaba Group); Yong Li (Alibaba Group)
Video Event Specification using Programmatic Composition: Daniel Y Fu (Stanford University); Will Crichton (Stanford University); James Hong (Stanford University); Xinwei Yao (Stanford University); Haotian Zhang (Stanford University); Anh Truong (Stanford University); Avanika Narayan (Stanford University); Maneesh Agrawala (Stanford University); Christopher Re (Stanford University); Kayvon Fatahalian (Stanford)
Efficient Inference at the Edge: George Cristian Muraru (University Politehnica of Bucharest); Costin Raiciu (UPB)
AliGraph: An Industrial Graph Neural Network Platform: Kun Zhao (Alibaba Group); Wencong Xiao (Alibaba Group); Baole Ai (Alibaba Group); Wenting Shen (Alibaba Group); Xiaolin Zhang (Alibaba Group); Yong Li (Alibaba Group); Wei Lin (Alibaba Group)
Adaptive Distributed Training of Deep Learning Models: Luo Mai (Imperial College London); Guo Li (Imperial College London); Andrei-Octavian Brabete (Imperial College London); Alexandros Koliousis (Imperial College London); Peter Pietzuch (Imperial College London)
Willump: Statistically-Aware Optimizations for Fast Machine Learning Inference: Peter Kraft (Stanford University); Daniel Kang (Stanford University); Deepak Narayanan (Stanford); Shoumik Palkar (Stanford); Peter D Bailis (Stanford University); Matei Zaharia (Stanford and Databricks)
Derecho’s Extensible, Intelligent Object Store: Weijia Song (Cornell University)
Fabrik: An online collaborative neural network editor: Utsav Garg (SAP Asia Pte Ltd); Viraj Prabhu (Georgia Tech); Deshraj Yadav (Tesla); Ram Ramrakhya (Inmobi); Harsh Agrawal (Georgia Institute of Technology); Dhruv Batra (Georgia Tech & Facebook AI Research)
Letting the Cloud Serve DNN Inferences with Ruthless Efficiency: Reza Karimi (Emory University); Anthony Simpson (Max Planck Institute for Software Systems); Antoine Kaufmann (Max Planck Institute for Software Systems); Ymir Vigfusson (Emory University); Jonathan Mace (Max Planck Institute for Software Systems)
FlexEnt: Entropy Coding to Curb Stragglers in Large-Scale Distributed Machine Learning: James M Salamy (Massachusetts Institute of Technology); Ayush Sharma (MIT); Manya Ghobadi (Massachusetts Institute of Technology); Muriel Medard (MIT)
Standardizing Evaluation of Neural Network Pruning: Jose Javier Gonzalez Ortiz (MIT); Davis Blalock (MIT); John Guttag (MIT)
Sparse Convolutions for Faster Object Recognition: Wei Hao (University of Wisconsin, Madison); Shivaram Venkataraman (University of Wisconsin, Madison)
The Case for a Learned Sorting Algorithm: Ani Kristo (Brown University); Kapil Vaidya (MIT); Ugur Cetintemel (Brown University); Tim Kraska (MIT)
EvalAI: Towards Better Evaluation of AI Agents: Deshraj Yadav (Tesla); Rishabh Jain (Georgia Tech); Harsh Agrawal (Georgia Institute of Technology); Prithvijit Chattopadhyay (Georgia Institute of Technology); Taranjeet Singh (JSS Academy of Technical Education, Noida); Akash Jain (Zomato); Shiv Baran Singh (JSS Academy of Technical Education, Noida
Training Larger Models on TensorFlow without Additional GPUs: Jinliang Wei (Carnegie Mellon University); Aurick Qiao (Petuum, Inc. and Carnegie Mellon University); Anand Jayarajan (University of Toronto, Vector Institute); Garth Gibson (Vector Institute); Vijay Vasudevan (Google Brain); Eric Xing (Petuum Inc. and CMU)
IntML: Natural Compression for Distributed Deep Learning: Samuel Horváth (KAUST); Chen-Yu Ho (KAUST); Ludovit Horvath (Comenius University); Atal Sahu (KAUST); Marco Canini (KAUST); Peter Richtarik (KAUST)