ml.bib

@ARTICLE{srivastava25,
  author={Srivastava, Satyam and Arunkumar, Akhil and Kurella, Nithesh and Panda, Amrit and Jain, Gaurav and Kamath, Purushotham and Wutzke, Mark and Tiruvur, Arun and Gupta, Mayank Mike and Soloveychik, Ilya and Darsi, Vamsi and Dalal, Malav and Patankar, Vinayak and Dudyala, Sasidhar and Duraisamy, Senthil and Ramchandran, Santhosh and Venkatasubramanian, Raghav and Qin, Yuwei and Wang, Xin and Balachandran, Jayaprakash and Gok, Ali Murat and Wojciechowski, Piotr and Ekanayake, Saliya and Ng, Chris and Sarma, Ranju and Rathore, Shubhankit and Trouwen, Tristan and Zhuang, Siwei and Nicol, Chris and Bhoja, Sudeep},
  journal={IEEE Micro}, 
  title={Corsair: An In-Memory Computing Chiplet Architecture for Inference-Time Compute Acceleration}, 
  year={2025},
  volume={45},
  number={5},
  pages={30-42},
  keywords={Computational modeling;Cognition;Bandwidth;Throughput;Tensors;Costs;Accuracy;Arithmetic;Memory management;Chiplets},
  doi={10.1109/MM.2025.3593444}
}




@inproceedings{adnan24,
 author = {Adnan, Muhammad and Arunkumar, Akhil and Jain, Gaurav and Nair, Prashant J. and Soloveychik, Ilya and Kamath, Purushotham},
 booktitle = {Proceedings of Machine Learning and Systems},
 editor = {P. Gibbons and G. Pekhimenko and C. De Sa},
 pages = {114--127},
 title = {Keyformer: KV Cache reduction through key tokens selection for Efficient Generative Inference},
 url = {https://proceedings.mlsys.org/paper_files/paper/2024/file/48fecef47b19fe501d27d338b6d52582-Paper-Conference.pdf},
 volume = {6},
 year = {2024}
}



@ARTICLE{abts20,
  AUTHOR = {D. Abts et. al.},
  TITLE = {{Think Fast: A Tensor Streaming Processor (TSP)
for Accelerating Deep Learning Workloads }},
 JOURNAL = {2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)},
  CITY = {},
  MONTH = {March},
  YEAR = {2020},
  PAGES = {},
  URL = {}
}


@ARTICLE{kamath18a,
  AUTHOR = {P. Kamath and A. Singh and D. Dutta},
  TITLE = {{Neural Architecture Construction using EnvelopeNets}},
  JOURNAL = {CoRR},
  CITY = {},
  MONTH = {March},
  YEAR = {2018},
  PAGES = {},
  URL = {http://arxiv.org/abs/1803.06744}
}

@ARTICLE{kamath18,
  AUTHOR = {P. Kamath and A. Singh and D. Dutta},
  TITLE = {{AMLA: an AutoML frAmework for Neural Network Design}},
  JOURNAL = {International Workshop on Automatic Machine Learning (AutoML Workshop 2018, at ICML 2018)},
  CITY = {Stockholm, Sweden},
  MONTH = {July},
  YEAR = {2018},
  PAGES = {},
  URL = {}
}

@ARTICLE{kamath18c,
  AUTHOR = {P. Kamath and A. Singh and D. Dutta},
  TITLE = {{Fast Neural Architecture Construction using EnvelopeNets}},
  JOURNAL = {International Workshop on MetaLearning (MetaLearning Workshop 2018, at NeurIPS 2018)},
  CITY = {Montreal, Canada},
  MONTH = {December},
  YEAR = {2018},
  PAGES = {},
  URL = {}