/AI5h ago

New Framework Edits Video Camera and Object Motion with 3D Point Tracks

4896259.3K
Original post
Jia-Bin Huang@jbhuang0604#321inAI

Hi friends at #CVPR2026! 馃憢

Please come check out our research today!

@YaoChihLee will showcase a super-fun video motion editing work - Edit-by-Track (#378)!

6:59 AM 路 Jun 6, 2026 路 5.5K Views
Sentiment

Positive users thank the poster for sharing SIMPACT's VLM robotic action planning debut at CVPR while negative users dismiss it as another routine unoriginal launch.

Pos
50.0%
Neg
50.0%
2 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS2.3KBOOKMARKS13LIKES27
Yilun Du@du_yilun

How can we effectively use VLMs for robotics manipulation?

Excited to share SIMPACT, which uses simulation as a tool to enable VLMs to reason and plan continuous robotics actions.

1hViews 2.3KLikes 27Bookmarks 13
RETWEETS1
Jia-Bin Huang@jbhuang0604

VLMs are great for their semantic reasoning capabilities.

BUT, they don't have a grounded understanding of physical dynamics.

So, we equip VLMs with physical reasoning through simulation-in-the-loop world modeling.

Come talk with Haowen about SIMPACT (#611): https://simpact-bot.github.io/

Jia-Bin Huang@jbhuang0604

Hi friends at #CVPR2026! 馃憢

Please come check out our research today!

@YaoChihLee will showcase a super-fun video motion editing work - Edit-by-Track (#378)!

5hViews 1.4KLikes 9Bookmarks 4
REPLIES2
Jia-Bin Huang@jbhuang0604

SIMPACT is live at 611!

1hViews 378Likes 6Bookmarks 0
Jia-Bin Huang@jbhuang0604

Robot learning is bottlenecked by data: adapting to new tasks, robots, and environments often requires many demonstrations.

Meet TraceGen! A motion world model that learns in a compact 3D trace space, abstracting away complex appearance.

This enables learning from diverse videos.

Meet @JayLEE_0301 at #605!

5hViews 1.1KLikes 4Bookmarks 2
Jia-Bin Huang@jbhuang0604

Customizing multiple visual concepts remains challenging.

We introduce UniVerse, a segmentation-free framework that learns to disentangle, localize, and recombine individual concepts within diffusion transformers.

Come check out the cool results by Quynh (#53). https://universe-personalization.github.io/

5hViews 427Likes 1Bookmarks 1
Jia-Bin Huang@jbhuang0604

I will be around all poster sessions!

Please come say HI!

5hViews 381Likes 2
Shaoxiong Yao@ShaoxiongYao

@jbhuang0604 Thank you Jia-Bin for posting!

39mViews 3
Strata@ChainZenit

@jbhuang0604 Another day, another chain launch. Seen it all before.

1hViews 3