Abhinav Gupta

4

Papers

88

Total Citations

Papers (4)

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning

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

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling