Multi-Modal Model series based on Patch-as-Decodable-Token framework.
PaDT
PaDT-MLLM
AI & ML interests
MultiModal Large Language Models
Recent Activity
upvoted a paper 3 days ago
UNITAS: A 3D-Native World Action Model for Embodied Manipulation liked a model 4 days ago
RobbinWang123/Unitas upvoted a paper 9 months ago
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and SecurityOrganizations
None yet