◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

J. Williams

4 papers hereh-index 220 citations5 works total

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

author position
  • first author3

Across the 3 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CL1
  • cs.CV1
  • cs.CY1
  • cs.LG1
same name
  • J. Williams — 36 papers, h 49
  • J. Williams — 28 papers
  • J. Williams — 18 papers, h 25
  • J. Williams — 10 papers, h 13
  • J. Williams — 9 papers, h 7
  • J. Williams — 9 papers, h 11

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

collaborators

4 papers

cs.LG2024

Rethinking Distance Metrics for Counterfactual Explainability

Joshua Nathaniel Williams, Anurag Katakkar, Hoda Heidari +1

Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by gen…

cs.CL2024

FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers

Joshua Nathaniel Williams, J. Zico Kolter

The widespread use of large language models has resulted in a multitude of tokenizers and embedding spaces, making knowledge transfer in prompt discovery tasks difficult. In this w…

cs.CV2024

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers

Joshua Nathaniel Williams, Avi Schwarzschild, Yutong He +1

Recovering natural language prompts for image generation models, solely based on the generated images is a difficult discrete optimization problem. In this work, we present the fir…

cs.CY2024

DrawL: Understanding the Effects of Non-Mainstream Dialects in Prompted Image Generation

Joshua N. Williams, Molly FitzMorris, Osman Aka +1

Text-to-image models are now easy to use and ubiquitous. However, prior work has found that they are prone to recapitulating harmful Western stereotypes. For example, requesting th…

◍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.