Folawiyo Campbell-Ajala — accepted AI-conference papers

2025

AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Christopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair +9

ICLR 2025poster

Autonomous agents that execute human tasks by controlling computers can enhance human productivity and application accessibility. However, progress in this field will be driven by realistic and reproducible benchmarks. We present AndroidWorld, a fully functional Android environment that provides rew…

Cited by 58 Source ↗PDF ↗code ↗Scholar ↗

2024

On the Effects of Data Scale on UI Control Agents

Wei Li, William E Bishop, Alice Li, Christopher Rawles, Folawiyo Campbell-Ajala, Divya Tyamagundlu +1

NeurIPS 2024spotlight

Autonomous agents that control user interfaces to accomplish human tasks are emerging. Leveraging LLMs to power such agents has been of special interest, but unless fine-tuned on human-collected task demonstrations, performance is still relatively low. In this work we study whether fine-tuning alone…

Cited by 14 Source ↗PDF ↗Scholar ↗

2024

UINav: A Practical Approach to Train On-Device Automation Agents

Wei Li, Fu-Lin Hsu, William Bishop, Folawiyo Campbell-Ajala, Max Lin, Oriana Riva

NAACL 2024industry

Automation systems that can autonomously drive application user interfaces to complete user tasks are of great benefit, especially when users are situationally or permanently impaired. Prior automation systems do not produce generalizable models while AI-based automation agents work reliably only in…

Cited by 6 Source ↗PDF ↗Scholar ↗