Elamur Research⌕
☰
home / authors / Jinfeng Rao

Jinfeng Rao

Jinfeng Rao has 3 papers in our library, in 2020–2023, most of them on Evaluation & benchmarks, Efficient models & compression; often with Donald Metzler, Yi Tay, Hyung Won Chung.

3 papers in our library · 2020–2023

OpenAlex · h-index 17 · 44 works · 1,070 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 460 citations in our library · 4 more in our library without a page yet · ⭐ Paper Star rank #2918

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

🏢PinterestSan Francisco2024–2026 · 2 paperscurrent🎓University of Maryland, College ParkCollege Park · United States2014–2020 · 14 papers🏢GoogleMountain View · United States2022–2023 · 7 papers🏢MetaMenlo Park · United States2019 · 3 papers🎓Nanyang Technological UniversitySingapore · Singapore2019 · 2 papers🎓The Ohio State UniversityColumbus · United States2019 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

 Topics

 Evaluation & benchmarks (1) Efficient models & compression (1)

 Works by year

2020s

20231 paper20221 paper20201 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Long Range Arena: A Benchmark for Efficient Transformers (2020 · 396 citations)
    Many "efficient" Transformer variants (xformers) have been proposed to get around the quadratic cost of self-attention.
  2. Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? (2023 · 79 citations)
    Most work on scaling laws studies only the standard Transformer. New architectures are also often judged at a single model size, such as "base", on the assumption that their gains carry over to other scales. This paper tests that assumption. The authors ask whether the inductive bias built into an architecture…
  3. Transcending Scaling Laws with 0.1% Extra Compute (2022 · 40 citations)
    Making large language models better usually means scaling them up, which costs a great deal of compute. The authors ask whether an already trained causal model can be improved cheaply instead. Their method, UL2R (UL2Restore), takes existing PaLM checkpoints and trains them for a small number of extra steps using the…

Also in our library

4 more works of theirs are in our library without a page here yet; they will appear as we publish them.

 Co-authors here

12 of 21 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 460 times (of the 140,884 papers whose bibliographies we read); 45 citing papers with a page here →.

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