Weihan Xu

WitneyWW

https://wx83.github.io/

wx83

AI & ML interests

None yet

Recent Activity

updated a Space about 17 hours ago

WitneyWW/action-to-camera-motion

published a Space about 17 hours ago

WitneyWW/action-to-camera-motion

updated a Space about 20 hours ago

WitneyWW/actionimage-mot-world-model-rollouts

View all activity

Organizations

None yet

updated a Space about 17 hours ago

Action to Camera Motion — a learned ActionImage

🧭

Predict dense camera motion from robot actions and visual state

published a Space about 17 hours ago

Action to Camera Motion — a learned ActionImage

🧭

Predict dense camera motion from robot actions and visual state

updated 2 Spaces about 20 hours ago

Action-Image MoT World Model — Rollouts, Short vs Long, Train vs Test

🎯

Explore predicted robot vision and touch rollouts

JavisDiT Edit — text_both_base_0728 step 71000

🎬

Explore video object add/remove edits with audio

published a Space about 20 hours ago

JavisDiT Edit — text_both_base_0728 step 71000

🎬

Explore video object add/remove edits with audio

updated a Space 1 day ago

JavisDiT Edit — text_both_base_0728 step 56000

🎬

Explore AI-generated object add/remove edits in videos

published a Space 1 day ago

JavisDiT Edit — text_both_base_0728 step 56000

🎬

Explore AI-generated object add/remove edits in videos

updated a Space 2 days ago

History-Conditioned MoT (no diffusion forcing) — Rollouts

⏮

Explore model predictions vs ground truth

published a Space 2 days ago

History-Conditioned MoT (no diffusion forcing) — Rollouts

⏮

Explore model predictions vs ground truth

updated a Space 3 days ago

JavisDiT Edit — text_both_base_0728 step 39000

🎬

Explore AI video object add/remove with audio previews

published a Space 3 days ago

JavisDiT Edit — text_both_base_0728 step 39000

🎬

Explore AI video object add/remove with audio previews

updated a Space 3 days ago

Tactile Retrieval Oracle Upper Limit

🦷

Explore tactile prediction limits with interactive visual report

published a Space 3 days ago

Tactile Retrieval Oracle Upper Limit

🦷

Explore tactile prediction limits with interactive visual report

published a Space 4 days ago

Action-Image MoT World Model — Rollouts, Short vs Long, Train vs Test

🎯

Explore predicted robot vision and touch rollouts

updated a Space 4 days ago

Action Images demo — pose → multi-view pixel actions

🎯

Generate multi‑view action images from robot pose data

published a Space 4 days ago

Action Images demo — pose → multi-view pixel actions

🎯

Generate multi‑view action images from robot pose data

updated a Space 4 days ago

JavisDiT Edit — text_both_base_0728 step 17000

🎬

Explore AI‑edited videos with object add/remove

published a Space 4 days ago

JavisDiT Edit — text_both_base_0728 step 17000

🎬

Explore AI‑edited videos with object add/remove

updated a Space 5 days ago

VGGT-Omega — three-view tabletop geometry

📐

Explore a three‑view 3D point‑cloud reconstruction online

published a Space 5 days ago

VGGT-Omega — three-view tabletop geometry

📐

Explore a three‑view 3D point‑cloud reconstruction online

Weihan Xu

AI & ML interests

Recent Activity

Organizations

WitneyWW's activity

Action to Camera Motion — a learned ActionImage

Action to Camera Motion — a learned ActionImage

Action-Image MoT World Model — Rollouts, Short vs Long, Train vs Test

JavisDiT Edit — text_both_base_0728 step 71000

JavisDiT Edit — text_both_base_0728 step 71000

JavisDiT Edit — text_both_base_0728 step 56000

JavisDiT Edit — text_both_base_0728 step 56000

History-Conditioned MoT (no diffusion forcing) — Rollouts

History-Conditioned MoT (no diffusion forcing) — Rollouts

JavisDiT Edit — text_both_base_0728 step 39000

JavisDiT Edit — text_both_base_0728 step 39000

Tactile Retrieval Oracle Upper Limit

Tactile Retrieval Oracle Upper Limit

Action-Image MoT World Model — Rollouts, Short vs Long, Train vs Test

Action Images demo — pose → multi-view pixel actions

Action Images demo — pose → multi-view pixel actions

JavisDiT Edit — text_both_base_0728 step 17000

JavisDiT Edit — text_both_base_0728 step 17000

VGGT-Omega — three-view tabletop geometry

VGGT-Omega — three-view tabletop geometry