H-EmbodVis

university

https://github.com/H-EmbodVis

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

dkliang authored a paper about 3 hours ago

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

dkliang submitted a paper about 8 hours ago

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

HENGFANG published a model 11 days ago

H-EmbodVis/PUMA

View all activity

Papers

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

View all Papers

H-EmbodVis 's Papers 5

Submitted by

Dingkang Liang

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

H-EmbodVis

15 1

Submitted by

Dingkang Liang

153

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

H-EmbodVis

220 4

Submitted by

Dingkang Liang

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

H-EmbodVis

328 5

Submitted by

Dingkang Liang

Towards Generalizable Robotic Manipulation in Dynamic Environments

H-EmbodVis

136 2

Submitted by

Dingkang Liang

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution

H-EmbodVis

359 2

AI & ML interests

Recent Activity

Papers

Team members 7

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Towards Generalizable Robotic Manipulation in Dynamic Environments

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution