Kris Kitani

10

Papers

50

Total Citations

Papers (10)

Real-Time Simulated Avatar from Head-Mounted Sensors

ExpertAF: Expert Actionable Feedback from Video

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

Flexible Depth Completion for Sparse and Varying Point Densities

ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives