◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Ananya Kumar

26 papers hereh-index 2011.5k citations37 works total

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

author position
  • first author5
  • middle author19
  • last author1

Across the 25 of 26 papers where every author was matched, so the position is known.

fields
  • cs.LG17
  • cs.CL5
  • cs.CV2
  • cs.CG1
  • cs.RO1
same name
  • Ananya Kumar — 3 papers, h 4
  • Ananya Kumar — 1 paper

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20172025
most citedFine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

160 citations · 461 across the 21 of their papers we have counts for

collaborators
Showing 2022 · cs.CVShow all

2 papers · 2 filters

cs.CV2022★ 4 cited

Finetune like you pretrain: Improved finetuning of zero-shot vision models

Sachin Goyal, Ananya Kumar, Sankalp Garg +2

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kuma…

cs.CV2022★ 5 cited

How to Fine-Tune Vision Models with SGD

Ananya Kumar, Ruoqi Shen, Sebastien Bubeck +1

SGD and AdamW are the two most used optimizers for fine-tuning large neural networks in computer vision. When the two methods perform the same, SGD is preferable because it uses le…

◍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.