Weihan Xu
AI & ML interests
Recent Activity
Organizations
Non-speech Audio+Video Removals — JAVEdit-100k & AVISet
Search video edits that remove objects and their sounds
InsAVE-80K Sample Viewer
Explore audio‑video editing samples with an interactive viewer
JavisDiT Edit — text_both_base_0728 step 104000 (20 test clips)
Add or remove objects in videos with matching audio
JavisDiT Edit — text_both_base_0728 step 85000 (full test set)
Explore AI-generated video object edits and metrics
Visuo-Tactile MoT - vmx injection rollouts
Explore ground‑truth vs prediction strips
Action to Camera Motion — a learned ActionImage
Predict dense camera motion from robot actions and visual state
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
JavisDiT Edit — text_both_base_0728 step 56000
Explore AI-generated object add/remove edits in videos
History-Conditioned MoT (no diffusion forcing) — Rollouts
Explore model predictions vs ground truth
JavisDiT Edit — text_both_base_0728 step 39000
Explore AI video object add/remove with audio previews
Tactile Retrieval Oracle Upper Limit
Explore tactile prediction limits with interactive visual report
Action Images demo — pose → multi-view pixel actions
Generate multi‑view action images from robot pose data
JavisDiT Edit — text_both_base_0728 step 17000
Explore AI‑edited videos with object add/remove
VGGT-Omega — three-view tabletop geometry
Explore a three‑view 3D point‑cloud reconstruction online
Point Cloud Sampling Strategies
Compare point‑cloud sampling methods interactively
JavisDiT Edit — text_both_base_0727 step 15000
Explore AI-edited videos with object addition and removal
Visuo-Tactile MoT World Model — Rollouts, Short vs Long, Train vs Test
Explore visuo‑tactile model rollouts and performance metrics
Point Cloud Voxel Downsampling
Downsample point clouds while preserving geometry
JavisDiT Edit — text_both_refwarmup_0724 step 49000
Explore AI-edited videos with objects added or removed
SAM-Audio Quality Textprompt vs New
Compare audio separation quality across pipelines
Tactile World Model — Where It Works and Where It Fails
Explore tactile model performance across conditions