VTWM vision-only — 40s long-horizon AR rollout

Diffusion-forcing world model rollouts. Each sample is ~2.7 s (16 raw frames @ 6 fps). Side-by-side videos show ground truth on the left, model prediction on the right. First half of each clip = history (GT), second half = autoregressively sampled future. Click a sample header to expand its videos (default-collapsed to keep the page light).

vision-only (val=0.0093) — 40s long-horizon AR

Pure visual prediction: num_views=3, num_tactiles=0. Ablation to see whether tactile helps visual prediction over long horizon.

Sections

Setup comparison

Click a run name to jump to its rollout videos. ✓ = feature on, ✗ = off. Lower val_loss is better.

run	fusion	views	tactile	shift16	delta-ref	cam-pose	gate	val_loss
12v_vision_only_val_0.0093	—	—	—	—	—	—	—	—

Rollout-latent metrics (10 val samples)

Latent-space MSE of predicted future vs ground truth. Contact/no-contact split uses tactile latent-to-reference energy (threshold 0.05).

run	view MSE	TL MSE	TR MSE	tactile contact MSE	tactile no-contact MSE
12v_vision_only_val_0.0093	1.737214	5.588249	5.637631	5.582695	5.658344

Other

12v_vision_only_val_0.0093

sample_000 (click to expand videos)

panel for 12v_vision_only_val_0.0093/sample_000

view_left — GT | rollout

view_middle (top-down) — GT | rollout

view_right — GT | rollout

tactile_left — GT | rollout

tactile_right — GT | rollout

sample_001 (click to expand videos)

panel for 12v_vision_only_val_0.0093/sample_001

view_left — GT | rollout

view_middle (top-down) — GT | rollout

view_right — GT | rollout

tactile_left — GT | rollout

tactile_right — GT | rollout

sample_002 (click to expand videos)

panel for 12v_vision_only_val_0.0093/sample_002

view_left — GT | rollout

view_middle (top-down) — GT | rollout

view_right — GT | rollout

tactile_left — GT | rollout

tactile_right — GT | rollout