Elamur Research⌕
☰
home / authors / Ramana Kumar

Ramana Kumar

Ramana Kumar has 2 papers in our library, in 2018–2022, most of them on Reasoning; often with Antonia Creswell, Cezary Kaliszyk, Francis Song.

2 papers in our library · 2018–2022

OpenAlex · ORCID · Wikidata · h-index 17 · 52 works · 1,116 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 371 times in our library · ⭐ Paper Stars ranking: #4919

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of CambridgeCambridge · United Kingdom2011–2025 · 12 papersEducation 2011–2015current🔬Data61Sydney · Australia2015–2020 · 15 papers🏛️Commonwealth Scientific and Industrial Research OrganisationCanberra · Australia2016–2019 · 13 papers🎓UNSW SydneySydney · Australia2015–2019 · 13 papers🏢Google DeepMindLondon · United Kingdom2018–2024 · 9 papersEmployment since 2018🏢GoogleMountain View · United States2020–2021 · 2 papers
🏛️Data61, CSIROSydney · Australia2015–2018Employment 2015–2018 · Trustworthy Systems

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksApplied Mathematics · 1 workArts and Humanities · 1 workLanguage and Linguistics · 1 workMathematics · 1 workComputational Theory and Mathematics · 1 work

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 2 works

 Works by year

2020s

20221 paper

2010s

20181 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Solving math word problems with process- and outcome-based feedback (2022 · 355 citations)
    Asking language models to write out step-by-step reasoning makes them better at reasoning tasks. Once you fine-tune instead of only prompting, though, you have to decide what to reward: just the final answer (outcome-based supervision) or every intermediate step (process-based supervision). The DeepMind team behind…
  2. TacticToe: Learning to Prove with Tactics (2018 · 57 citations)
    In interactive theorem provers such as HOL4, users build proofs by applying tactics, high-level steps that transform a goal into simpler subgoals.

 Co-authors here

10 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 371 times (of the 149,439 papers whose bibliographies we read); 164 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ramana-kumar/