Yunzhu Li

Affiliations

MIT

papers

813

total citations

papers (14)

PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

ICCV 2025arXiv

citations

PhysGen3D: Crafting a Miniature Interactive World from a Single Image

CVPR 2025arXiv

citations

Model-Based Control with Sparse Neural Dynamics

NEURIPS 2023arXiv

citations

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

CVPR 2024arXiv

citations

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

NEURIPS 2023arXiv

citations

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

NEURIPS 2025arXiv

citations

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

CVPR 2023arXiv

citations

Intelligent Carpet: Inferring 3D Human Pose From Tactile Signals

CVPR 2021

citations

ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment

NEURIPS 2022

citations

Yunzhu Li

Affiliations

papers (14)

Executable Code Actions Elicit Better LLM Agents

Causal Discovery in Physical Systems from Videos

Learning Physical Graph Representations from Visual Scenes

Reinforcement Learning with Neural Radiance Fields

The ObjectFolder Benchmark: Multisensory Learning With Neural and Real Objects

PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

PhysGen3D: Crafting a Miniature Interactive World from a Single Image

Model-Based Control with Sparse Neural Dynamics

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

Intelligent Carpet: Inferring 3D Human Pose From Tactile Signals

ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment

papers (14)

Executable Code Actions Elicit Better LLM Agents

Causal Discovery in Physical Systems from Videos

Learning Physical Graph Representations from Visual Scenes

Reinforcement Learning with Neural Radiance Fields

The ObjectFolder Benchmark: Multisensory Learning With Neural and Real Objects

PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

PhysGen3D: Crafting a Miniature Interactive World from a Single Image

Model-Based Control with Sparse Neural Dynamics

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

Intelligent Carpet: Inferring 3D Human Pose From Tactile Signals

ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment