Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work? (2020 · 281 citations)
Training a pretrained encoder on a large auxiliary dataset before fine-tuning it on the final task (the STILTs approach) sometimes improves results and sometimes does not, and the reasons are poorly understood.
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training (2026 · 4 citations)
Reinforcement-learning training of GUI agents needs many interactive environments. Existing benchmarks such as WebArena or OSWorld are built by hand and cover only a limited number of applications. InfiniteWeb addresses this by automatically synthesizing complete multi-page websites together with tasks and…
From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation (2026 · 1 citation)
End-to-end GUI agents, which map screenshots directly to actions, are simpler to deploy than framework-based computer-use systems but score noticeably lower on OSWorld-Verified.

Co-authors here

12 of 13 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 124 times (of the 149,439 papers whose bibliographies we read); 27 citing papers with a page here →.

Updated 31 October 2026