✳flâneur — a map of the web's best reading

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

pku-epic.github.io · 719 words · saved by 1 readers

The model jointly denoises action chunks and future DINO sequences within a unified multi-modal diffusion transformer framework. Heterogeneous data play distinct yet complementary roles for learning visual forecasting, dynamics learning and policy.

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion Paper Code Data (Coming Soon) Checkpoints LDA-1B is a dynamics-centric robot foundation model trained on 30k+ hours of heterogeneous embodied data . It jointly learns dynamics , visual forecasting , and policy in a unified latent space , enabling scalable learning beyond BC. Universal Embodied Data Ingestion Unified Latent Dynamics and Policy Learning The model jointly denoises action chunks and future DINO sequences within a unified multi-modal diffusion transformer framework. Heterogeneous data play distinct y

Explore this link on the map →

saved by

related reading