H-EmbodVis

university

https://github.com/H-EmbodVis

AI & ML interests

None defined yet.

Recent Activity

CFYao updated a model about 2 hours ago

H-EmbodVis/TurboVLA

CFYao published a model 1 day ago

H-EmbodVis/TurboVLA

dkliang submitted a paper 2 days ago

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

View all activity

Papers

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

View all Papers

H-EmbodVis 's papers 7

Submitted by

Dingkang Liang

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

H-EmbodVis

Submitted by

Xin Zhou

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

H-EmbodVis

Submitted by

Dingkang Liang

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

H-EmbodVis

Submitted by

Dingkang Liang

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

H-EmbodVis

Submitted by

Dingkang Liang

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

H-EmbodVis

Submitted by

Dingkang Liang

Towards Generalizable Robotic Manipulation in Dynamic Environments

H-EmbodVis

Submitted by

Dingkang Liang

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

H-EmbodVis