Shadowgraph
TrendingBuzzResearch
Chrome extension
Sign in

yinchenghust/simplememvla_libero

Model

SimpleMemVLA

0

4 commits

2 linked in READMEs

updated Sep 9, 2026

See the code

README

SimpleMemVLA

SimpleMemVLA is a Vision-Language-Action (VLA) model for long-horizon robot manipulation with a native-video memory mechanism. It keeps the sampled history intact and processes it as timestamped video through the backbone, using the hidden states of a generated sub-task to condition a flow-matching action head.

Paper: SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

Project page: https://huggingface.co/collections/yinchenghust/simplememvla

Code: https://github.com/wadeKeith/SimpleMemVLA

endpoints_compatible
robotics
safetensors
simplememvla
transformers

Similar repos

yinchenghust/simplememvla_robomemarena

Model

SimpleMemVLA

0

yinchenghust/simplememvla_mikasa

Model

SimpleMemVLA

0

yinchenghust/simplememvla_robomme

Model

SimpleMemVLA

0

yinchenghust/simplememvla_rmbench

Model

SimpleMemVLA

0

yinchenghust/rmbench_lerobot

Dataset

SimpleMemVLA Dataset

0

yinchenghust/libero_lerobot

Dataset

SimpleMemVLA Dataset

0

OpenBMB/SimpleMemVLA

Native-video memory for vision-language-action models, using timestamped visual history and exact…

88

yinchenghust/mikasa_lerobot

Dataset

SimpleMemVLA Datasets

0

Linked in READMEs

OpenBMB/SimpleMemVLA

Native-video memory for vision-language-action models, using timestamped visual history and exact…

88

README badge

wadeKeith/SimpleMemVLA

This project has moved to https://github.com/OpenBMB/SimpleMemVLA.

0

README badge

yinchenghust/simplememvla_libero

Model

SimpleMemVLA

0

4 commits

2 linked in READMEs

updated Sep 9, 2026

See the code

README

SimpleMemVLA

SimpleMemVLA is a Vision-Language-Action (VLA) model for long-horizon robot manipulation with a native-video memory mechanism. It keeps the sampled history intact and processes it as timestamped video through the backbone, using the hidden states of a generated sub-task to condition a flow-matching action head.

Paper: SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

Project page: https://huggingface.co/collections/yinchenghust/simplememvla

Code: https://github.com/wadeKeith/SimpleMemVLA

endpoints_compatible
robotics
safetensors
simplememvla
transformers

Similar repos

yinchenghust/simplememvla_robomemarena

Model

SimpleMemVLA

0

yinchenghust/simplememvla_mikasa

Model

SimpleMemVLA

0

yinchenghust/simplememvla_robomme

Model

SimpleMemVLA

0

yinchenghust/simplememvla_rmbench

Model

SimpleMemVLA

0

yinchenghust/rmbench_lerobot

Dataset

SimpleMemVLA Dataset

0

yinchenghust/libero_lerobot

Dataset

SimpleMemVLA Dataset

0

OpenBMB/SimpleMemVLA

Native-video memory for vision-language-action models, using timestamped visual history and exact…

88

yinchenghust/mikasa_lerobot

Dataset

SimpleMemVLA Datasets

0

Linked in READMEs

OpenBMB/SimpleMemVLA

Native-video memory for vision-language-action models, using timestamped visual history and exact…

88

README badge

wadeKeith/SimpleMemVLA

This project has moved to https://github.com/OpenBMB/SimpleMemVLA.

0

README badge