Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
LaMem-VLA introduces a latent-memory-native framework that integrates historical experience into vision-language-action reasoning through coordinated memory components operating in…
Hugging Face · Daily Papers
·Hongyu Qu, Jianzhe Gao
·
·▲ 51 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Hongyu Qu, Jianzhe Gao, Xiaobin Hu, Shaohuan Yang, Xinlei Yu, Rui Yan
- 51 upvotes da comunidade
- Temas: Vision-Language-Action models, Markovian assumption, memory-augmented VLAs, latent embedding space, latent memory tokens, short-term memory vaults
Resumo
Resumo original (em inglês), extraído do paper:
LaMem-VLA introduces a latent-memory-native framework that integrates historical experience into vision-language-action reasoning through coordinated memory components operating in the same latent space.