SimpleMemVLA
Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon robot manipulation.
- 115
- Python
- MIT
- 3 wk ago
Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon robot manipulation.
ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream