◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Prémkumar Dévanbu

8 papers here

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author6
  • last author2

Across the 8 of 8 papers where every author was matched, so the position is known.

fields
  • cs.SE6
  • cs.CR1
  • cs.PL1
ORCID 0000-0002-4346-5276

identity via Semantic Scholar / OpenAlex

activity
20142024
most citedFew-shot training LLMs for project-specific code-summarization

10 citations · 48 across the 8 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

cs.PL2022★ 9 cited

NatGen: Generative pre-training by "Naturalizing" source code

Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding +2

Pre-trained Generative Language models (e.g. PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and…

cs.SE2022★ 10 cited

Few-shot training LLMs for project-specific code-summarization

Toufique Ahmed, Premkumar Devanbu

Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A par…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.