[KongchangAI]
ModelUI-TARS-2B

UI-TARS-2B

A 2B-parameter vision-language model for UI grounding tasks that performs poorly in zero-shot settings.

Timeline (last 90 days)

Nov 17

On point-in-box accuracy, the 279M ranker reaches 73.4%, zero-shot UI-TARS-2B reaches 29.6%, and Qwen2.5-VL-7B reaches 23.7%.

Unverified50%

All Facts (1)

Source Articles