VTWM tactile-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).

tactile-only (val=0.0062) — 40s long-horizon AR

Pure tactile prediction: num_views=0, num_tactiles=2. Loss scale ≠ multi-modal baseline; compare against baseline's tactile slice.

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
13t_tactile_only_val_0.0062	—	—	—	—	—	—	—	—

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
13t_tactile_only_val_0.0062	n/a	1.979452	2.168195	2.061119	2.059416

Other

13t_tactile_only_val_0.0062

sample_000 (click to expand videos)

tactile_left — GT | rollout

tactile_right — GT | rollout

sample_001 (click to expand videos)

panel for 13t_tactile_only_val_0.0062/sample_001

tactile_left — GT | rollout

tactile_right — GT | rollout

sample_002 (click to expand videos)

panel for 13t_tactile_only_val_0.0062/sample_002

tactile_left — GT | rollout

tactile_right — GT | rollout