UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...
Specifications
- Provider
- ByteDance
- Type
- Open-source / open-weight
- Modality
- text+image->text
- Context window
- 128K
- Knowledge cutoff
- 2025-01-31
- Released
- July 22, 2025
Capabilities
Input: imageInput: textOutput: text
Strengths
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
