Native Video-Action Pretraining for Generalizable Robot Control
The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments. To bridge this gap, we present LingBot-VA 2.0, a video-action foundation model built from the ground up for embodiment. Four core design principles showcase its evolution from LingBot-VA. (1) Departing from traditional reconstruction-focused VAEs, we introduce a semantic visual-action tokenizer, which aligns visual representations with both semantics and actions, imp
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorLuyao Zhang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorQihang Zhang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorHanlin Liu →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorShuai Yang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYiming Luo →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorShuaiting Li →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorRuilin Wang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorJunke Wang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorJiahao Shao →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorGangwei Xu →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorJiaming Zhou →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYishu Shen →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYudong Jin →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorFangyi Xu →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorShuailei Ma →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorJiaqi Liao →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorGuanxing Lu →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorZifan Shi →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYongkun Wen →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYujie Zhao →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorWeixuan Tang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorXinyang Wang →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorChaojian Li →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorJiapeng Zhu →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorKa Leong Cheng →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorNan Xue →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorXing Zhu →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYujun Shen →
Native Video-Action Pretraining for Generalizable Robot Control
- Linked via arxiv authorYinghao Xu →
Native Video-Action Pretraining for Generalizable Robot Control