Unverified50% confidenceFactExact time
RT-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
1
Sources
50%
Confidence
Long-term
Relevance
8/21/2026
First Seen
Sources
Related Claims
UnverifiedRT-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76% similarVerifiedThe model belongs to the category of Vision-Language-Action (VLA) models, unifying a visual encoder, a language understanding module, and an action prediction head within an end-to-end architecture.64% similarUnverifiedLLM 0.32a0 introduced two core changes: modeling model input as a sequence of messages, and modeling model responses as typed streaming parts63% similarUnverifiedThe tool-calling mechanism allows large language models to dynamically invoke external functions during inference, representing a fundamental leap from language models to action models.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/783809API
curl https://kongchang.com/api/v1/knowledge/claims/783809MCP
get_claim(id=783809)