Minwoo (Josh) Kang
email: mkang at cs
dot berkeley dot edu
dot berkeley dot edu
Hi, I’m a PhD student in CS at UC Berkeley, where I am part of Berkeley AI Research (BAIR) and the SLICE Lab.
My research is advised by Prof. John Canny and Prof. John Wawrzynek.
I am broadly interested in research topics within computational linguistics and digital hardware design:
- Artifical language agents: improving LM-LM and Human-LM collaboration
- Computational sociolinguistics: use of LLMs as viritual human subjects
- LLMs as aids for automated formal reasoning: applications in hardware design and formal verification
Work
- 2024.01 - Present
- 2022.05 - 2023.05
Student Researcher / HW Engineering Intern
Google
Research on ML-based Formal Verification with Google CI2
Publications
2024
- DiffSampler: Differential and Massively Parallel Sampling of SAT FormulasIn Proceedings of the 61st ACM/IEEE Design Automation Conference (DAC), 2024
2023
- LFPS: Learned Formal Proof Stengthening for Efficient Hardware VerificationIn Proceedings of the 42nd IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2023
- Narrowing the Synthesis Gap: Academic FPGA Synthesis is Catching Up With the IndustryIn 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2023
- Full Stack Optimization of Transformer Inference: a SurveyarXiv preprint arXiv:2302.14017, 2023
2021
- CoSA: Scheduling by Constrained Optimization for Spatial AcceleratorsIn 2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), 2021
- Turning Around and Around: Motion Planning through Thick and Thin TurnstilesIn 33rd Canadian Conference on Computational Geometry (CCCG), 2021