Yuke Zhu

papers

2,636

total citations

papers (18)

Coopernaut: End-to-End Driving With Cooperative Perception for Networked Vehicles

CVPR 2022arXiv

160

citations

Ditto: Building Digital Twins of Articulated Objects From Interaction

CVPR 2022arXiv

150

citations

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

ICCV 2021arXiv

citations

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

NEURIPS 2020arXiv

citations

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

CVPR 2022arXiv

citations

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

CVPR 2021arXiv

citations

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

CVPR 2023arXiv

citations

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

AAAI 2024arXiv

citations

Cross-Episodic Curriculum for Transformer Agents

NEURIPS 2023arXiv

citations

Spherical Feature Transform for Deep Metric Learning

ECCV 2020arXiv

citations

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

ICLR 2025

citations

RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition

ECCV 2020

citations

LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions

ICCV 2025arXiv

citations

Yuke Zhu

papers (18)

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Eureka: Human-Level Reward Design via Coding Large Language Models

Pre-Trained Language Models for Interactive Decision-Making

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Coopernaut: End-to-End Driving With Cooperative Perception for Networked Vehicles

Ditto: Building Digital Twins of Articulated Objects From Interaction

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

Cross-Episodic Curriculum for Transformer Agents

Spherical Feature Transform for Deep Metric Learning

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition

LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions

papers (18)

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Eureka: Human-Level Reward Design via Coding Large Language Models

Pre-Trained Language Models for Interactive Decision-Making

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Coopernaut: End-to-End Driving With Cooperative Perception for Networked Vehicles

Ditto: Building Digital Twins of Articulated Objects From Interaction

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

Cross-Episodic Curriculum for Transformer Agents

Spherical Feature Transform for Deep Metric Learning

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition

LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions