We open-source the Uplink Massive MU-MIMO with Coherent and Non-coherent Array dataset collected to experiment with distributed beamforming in the presence of time and frequency offset.
We open-source the Multi-User MIMO dataset for examining the inter-user channel correlation in a real-world propagation environment.
We open-source our HW-NAS-Bench which is the first public dataset for Hardware-Neural Architecture Search aimed at democratizing research to non-hardware experts and make HW-NAS research more reproducible, and accessible for the community.
We open-source the AutoDNNchip tool which is an automated Deep Neural Network chip generator for both FPGA and ASIC DNN chip implementations.
PI Lin lab's proposal titled "Workshop on Automated AI Tools for Computing and Communication" has been selected by Rice University as one amongst the thirteen proposals under Creative Ventures Funds 2022 with an award of $10,000 as workshop development fund.
PI Lin lab will be organizing a "Tutorial on Automated Tools for Fast Development of Deep Learning Networks and Accelerators " which has been accepted as amongst the top proposals at IEEE/ACM MICRO 2022 to be held in Chicago, IL.
PI Lin gave invited talks at Google, Hewlett-Packard, and the Efficient Deep Learning for Computer Vision CVPR Workshop at the CVPR 2021 conference, sharing our achieved results.
PI Sabharwal participated in an academic-corporate panel in International Symposium on Information Theory (ISIT 2021) that discussed the grand challenges for future wireless networks.
PI Cavallaro gave an invited talk at Texas A&M University in April 2021 on Architectures, and Testbeds for Wireless Communication Systems related to the 3DML project.
Graduate student Chaojian Li presented his work “HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark” as a spotlight paper (i.e., ranking top 3%) at International Conference on Learning Representations (ICLR 2021), in a virtual format.
Graduate student Yonggan Fu presented his work “A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning” in the 58th Design Automation Conference (DAC 2021), in a virtual format.
Graduate students Yiming Qiu and Hongyi Liu presented their work “Towards Reconfigurable Kernel Datapaths with Learned Optimizations” at the workshop on Hot Topics in Operating Systems (HotOS 2021), in a virtual format.
Postdoc researcher Mengquan Li presented her work “O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed” in the IEEE/ACM International Conference on Computer-Aided Design (ICCAD 2021), in a virtual format.
PI Sabharwal gave the keynote address at ACM Mobihoc 2020 on the new research frontiers for wireless research.
Rahman Doost-Mohammady, Mehdi Zafari and Ashutosh Sabharwal, "Robustness of Distributed Multi-User Beamforming: An Experimental Evaluation", 2022 IEEE 12th Sensor Array and Multichannel Signal Processing Workshop 2022 (SAM 2022).
S P Sharan, Wenqing Zheng, Kuo-feng Xu, Jiarong Xing, Ang Chen and Zhangyang Wang, "Symbolic Distillation for Learned TCP Congestion Control". Under Review at NeurIPS 2022.
Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Yingyan Lin, “HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark”, The 9th International Conference on Learning Representations 2021 (ICLR 2021).
Yonggan Fu, Yongan Zhang, Chaojian Li, Zhongzhi Yu, Yingyan Lin, “A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning”, The 58th Design Automation Conference 2021 (DAC 2021).
Mengquan Li, Zhongzhi Yu, Yongan Zhang, Yonggan Fu, Yingyan Lin, “O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed”, The 40th IEEE/ACM International Conference on Computer Aided Design 2021 (ICCAD 2021).
Yiming Qiu, Hongyi Liu, Thomas Anderson, Yingyan Lin, Ang Chen, “Toward Reconfigurable Kernel Datapaths with Learned Optimizations”, The 18th Workshop on Hot Topics in Operating Systems (HotOS 2021).
Chance Tarver, Alexios Balalsoukas-Slimining, Christoph Studer and Joseph R. Cavallaro, "Virtual DPD Neural Network Predistortion for OFDM-based MU-Massive MIMO," 2021 55th Asilomar Conference on Signals, Systems, and Computers, 2021 (ACSSC 2021).
Chance Tarver, Alexios Balatsoukas-Stimming, Christoph Studer and Joseph R. Cavallaro, "OFDM-Based Beam-Oriented Digital Predistortion for Massive MIMO," 2021 IEEE International Symposium on Circuits and Systems 2021 (ISCAS 2021).
Graduate student Chance Tarver submitted his PhD dissertation titled "Nonlinearity Correction in Massive MIMO Systems via Virtual DPD" in Summer 2022. Advisor: PI Cavallaro, Rice University.