Yash Kant

9

Papers

71

Total Citations

Papers (9)

SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation

Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior

Pippo: High-Resolution Multi-View Humans from a Single Image

Contrast and Classify: Training Robust VQA Models

Spatially Aware Multimodal Transformers for TextVQA

LaTeRF: Label and Text Driven Object Radiance Fields

Housekeep: Tidying Virtual Households Using Commonsense Reasoning

SPAD: Spatially Aware Multi-View Diffusers

Invertible Neural Skinning