Deformable Convolutional Networks

Deformable Convolutional Networks

Associative Embedding= End-to-End Learning for Joint Detection and Grouping

Associative Embedding= End-to-End Learning for Joint Detection and Grouping

CenterNet

CenterNet

Language Models as Zero-Shot Planners= Extracting Actionable Knowledge for Embodied Agents
Vision-Language Interpreter for Robot Task Planning

Vision-Language Interpreter for Robot Task Planning

RoboEXP

RoboEXP

Pixtral 12B
OpenPose Using Part Affinity Fields

OpenPose Using Part Affinity Fields

(Mindmap) Part-level Scene Understanding for Robots

(Mindmap) Part-level Scene Understanding for Robots

ConceptAgent= LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution