Popular repositories Loading

1. ViewCraft ViewCraft Public

   Evolving what multimodal agents see and how they read it. Framework, ten reusable task skills, and paper resources.

   Python 21

2. AutoVisualSkill AutoVisualSkill Public

   everything to skill

   Python 11

3. M2A M2A Public

   M2A is a personalized multimodal agent framework with dual-layer hybrid memory designed for long-term human-machine interactions.

   Python 10 2

4. AD-MIR AD-MIR Public

   AD-MIR is a multimodal reasoning agent designed for bridging the gap from perception to persuasion in advertising video understanding.

   Python 5 1

5. ViewCraft-page ViewCraft-page Public

   Project page for ViewCraft: Evolving What Multimodal Agents See and How They Read It.

   HTML