Unverified50% confidenceFactExact time
The suspected new model supports both text-to-image (t2i) and image-to-image (i2i) capabilities simultaneously.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
UnverifiedEach model was run using either Terminus-2 or one of three native harnesses66% similarUnverifiedThe proposal suggests establishing two separate tag categories: 'New Fine-tuned Model' and 'New Base Model'.59% similarUnverifiedRT-2的基座是280亿参数的PaLM-E模型，动作被编码为离散token序列，与语言token在同一自回归框架下生成59% similarUnverifiedCognition has launched a new-generation programming model, SWE-2.58% similarUnverifiedRT-2（2023年）将55B参数的视觉-语言模型PaLM-E微调为可直接输出离散化动作token的策略模型58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933001API
curl https://kongchang.com/api/v1/knowledge/claims/933001MCP
get_claim(id=933001)