| A hardware–software blueprint for flexible deep learning specialization T Moreau, T Chen, L Vega, J Roesch, E Yan, L Zheng, J Fromm, Z Jiang, ... IEEE Micro 39 (5), 8-16, 2019 | 198 | 2019 |
| Relay: A new ir for machine learning frameworks J Roesch, S Lyubomirsky, L Weber, J Pollock, M Kirisame, T Chen, ... Proceedings of the 2nd ACM SIGPLAN international workshop on machine …, 2018 | 138 | 2018 |
| A metaprogramming framework for formal verification G Ebner, S Ullrich, J Roesch, J Avigad, L de Moura Proceedings of the ACM on Programming Languages 1 (ICFP), 1-29, 2017 | 124 | 2017 |
| Fuzzing the Rust typechecker using CLP (T) K Dewey, J Roesch, B Hardekopf 2015 30th IEEE/ACM International Conference on Automated Software …, 2015 | 100 | 2015 |
| Dynamic tensor rematerialization M Kirisame, S Lyubomirsky, A Haan, J Brennan, M He, J Roesch, T Chen, ... arXiv preprint arXiv:2006.09616, 2020 | 91 | 2020 |
| Axiomatic foundations and algorithms for deciding semantic equivalences of SQL queries S Chu, B Murphy, J Roesch, A Cheung, D Suciu arXiv preprint arXiv:1802.02229, 2018 | 76 | 2018 |
| Language fuzzing using constraint logic programming K Dewey, J Roesch, B Hardekopf Proceedings of the 29th ACM/IEEE international conference on Automated …, 2014 | 63 | 2014 |
| Nimble: Efficiently compiling dynamic neural networks for model inference H Shen, J Roesch, Z Chen, W Chen, Y Wu, M Li, V Sharma, Z Tatlock, ... Proceedings of Machine Learning and Systems 3, 208-222, 2021 | 58 | 2021 |
| Tea: A high-level language and runtime system for automating statistical analysis E Jun, M Daum, J Roesch, S Chasins, E Berger, R Just, K Reinecke Proceedings of the 32nd Annual ACM Symposium on User Interface Software and …, 2019 | 46 | 2019 |
| Improved type specialization for dynamic scripting languages MN Kedlaya, J Roesch, B Robatmili, M Reshadi, B Hardekopf Proceedings of the 9th Symposium on Dynamic Languages, 37-48, 2013 | 35 | 2013 |
| Relay: A high-level compiler for deep learning J Roesch, S Lyubomirsky, M Kirisame, L Weber, J Pollock, L Vega, ... arXiv preprint arXiv:1904.08368, 2019 | 32 | 2019 |
| Bring your own codegen to deep learning compiler Z Chen, CH Yu, T Morris, J Tuyls, YH Lai, J Roesch, E Delaye, V Sharma, ... arXiv preprint arXiv:2105.03215, 2021 | 19 | 2021 |
| Relay: A high-level IR for deep learning J Roesch, S Lyubomirsky, M Kirisame, J Pollock, L Weber, Z Jiang, ... arXiv preprint arXiv:1904.08368, 2019 | 16 | 2019 |
| Theia: automatically generating correct program state visualizations J Pollock, J Roesch, D Woos, Z Tatlock Proceedings of the 2019 ACM SIGPLAN Symposium on SPLASH-E, 46-56, 2019 | 11 | 2019 |
| Automated data structure generation: Refuting common wisdom K Dewey, L Nichols, B Hardekopf 2015 IEEE/ACM 37th IEEE International Conference on Software Engineering 1 …, 2015 | 10 | 2015 |
| Relax: Composable Abstractions for End-to-End Dynamic Machine Learning R Lai, J Shao, S Feng, SS Lyubomirsky, B Hou, W Lin, Z Ye, H Jin, Y Jin, ... arXiv preprint arXiv:2311.02103, 2023 | 9 | 2023 |
| An architecture supporting formal and compositional binary analysis J McMahan, M Christensen, L Nichols, J Roesch, SY Guo, B Hardekopf, ... ACM SIGARCH Computer Architecture News 45 (1), 177-191, 2017 | 9 | 2017 |
| Optimizing machine learning models M Welsh, J Knight, J Roesch, T Moreau, A Chang, T Chen, LH Ceze, ... US Patent 11,216,752, 2022 | 3 | 2022 |
| LastLayer: Toward hardware and software continuous integration L Vega, J Roesch, J McMahan, L Ceze IEEE Micro 40 (4), 103-111, 2020 | 3 | 2020 |
| Principled Optimization of Dynamic Neural Networks J Roesch University of Washington, 2020 | 2 | 2020 |
Tianqi ChenCarnegie Mellon UniversityVerified email at cmu.edu