[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

[NeurIPS 2025 Spotlight] SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

🌴[CVPR 2024] OakInk2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion

Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty

Precision-Focused Reinforcment Learning for Robotic Object Pushing

Improving Robotic Arms through Natural Language Processing, Computer Vision, and Edge Computing

Implementation of a cycle consistency GAN for object transfiguration applied to fruit images.

Demonstration for the Qwen/Qwen-Image-Edit-2511 model, specialized in object manipulation via lazy-loaded LoRA adapters. Supports adding or removing specific elements (e.g., logos, accessories, clothing) in single- or multi-image inputs while preserving lighting, realism, and background details. Features precise prompt control and fast inference.

In high school, I built a 3D Pong game using Python and the VPython library to explore game development. The game features paddles, a ball, and collision detection in a 3D environment, with difficulty levels and scoring. This project helped me learn programming basics, 3D object manipulation, and event-driven game loops. (December 2021)