sadjava's picture
Add model card
43499a6 verified
|
Raw History Blame Contribute Delete
857 Bytes
metadata
tags:
  - libero
  - latent-dynamics
  - action-free
  - robotics
  - shuffled-future
  - control

Latent dynamics (IDM/FDM) · libero_90 · seed 1000 · shuffled-future control

Action-free visual dynamics pretrain: frozen SmolVLA vision features → IDM → FDM. Trained on RGB from nvidia/libero_90 only (no action / state / reward labels).

Control run: trained with shuffle_future=True — the future RGB frame is sampled from a different episode, so temporal dynamics are broken. Same architecture / steps / data volume as the real IDM; use as a negative control for video-latent fine-tuning (VIDEO_CKPT=.../idm_fdm.pt from this repo).

Files:

  • idm_fdm.pt — model weights + config dict
  • idm_fdm.json — training hyperparameters

Used as frozen teacher for video-latent few-shot SmolVLA fine-tuning (--video.checkpoint).