MintAct: A Unified Visual Agent for Digital Environments
MintAct vision-language models at 2B, 4B, and 8B unify UI grounding, multi-step navigation, and visual tool use, matching per-domain specialists.
1 stories, newest first · one card per story
MintAct vision-language models at 2B, 4B, and 8B unify UI grounding, multi-step navigation, and visual tool use, matching per-domain specialists.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views