UItron, trained with multi-stage SFT and curriculum RL on a new 1M-step Chinese app dataset, beats prior GUI agents on perception, grounding, planning, and especially Chinese mobile app scenarios.
Visionllm: Large language model is also an open-ended decoder for vision-centric tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
UItron: Foundational GUI Agent with Advanced Perception and Planning
UItron, trained with multi-stage SFT and curriculum RL on a new 1M-step Chinese app dataset, beats prior GUI agents on perception, grounding, planning, and especially Chinese mobile app scenarios.