Scholar
Nishant Subramani
Google Scholar ID: x9-p03gAAAAJ
PhD student at CMU
Citations & Impact
Citations
4,007
H-index
14
i10-index
14
Publications
20
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Wrote the first papers on steering vectors (NeurIPS2019, arXiv2020, ACL2022). Worked on open LLM initiatives such as OLMo and BLOOM, winning multiple best paper awards and a GeekWire innovation of the year award.
Research Experience
- Interned at the semantic machines team at Microsoft Research and the cloud AI research team at Google working on actionable interpretability. Spent nearly two and a half years as a predoctoral researcher on the AllenNLP team at AI2, where I worked with Matt Peters. Before that, spent two years in industry at startups as a research scientist working on NLP, vision, speech, and multimodal applications.
Education
- 3rd year PhD student at CMU in the Language Technologies Institute (LTI), advised by Mona Diab.
Background
- Primarily interested in demystifying language model internals (MechInterp) and operationalizing them (ActionableInterp) to build more responsible, controllable, trustworthy, and efficient NLP systems.
Miscellany
- Interested in chatting and perhaps collaborating and/or mentoring, especially if you are from an underrepresented group.
