Picture for Xiangyang Ji

Xiangyang Ji

Tsinghua University, Beijing, China

EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera

Add code
Dec 16, 2024
Viaarxiv icon

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

Add code
Dec 15, 2024
Viaarxiv icon

Falcon-UI: Understanding GUI Before Following User Instructions

Add code
Dec 12, 2024
Viaarxiv icon

Street Gaussians without 3D Object Tracker

Add code
Dec 07, 2024
Viaarxiv icon

GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024

Add code
Dec 03, 2024
Viaarxiv icon

EventGPT: Event Stream Understanding with Multimodal Large Language Models

Add code
Dec 01, 2024
Viaarxiv icon

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

Add code
Nov 25, 2024
Viaarxiv icon

Doubly Mild Generalization for Offline Reinforcement Learning

Add code
Nov 13, 2024
Figure 1 for Doubly Mild Generalization for Offline Reinforcement Learning
Figure 2 for Doubly Mild Generalization for Offline Reinforcement Learning
Figure 3 for Doubly Mild Generalization for Offline Reinforcement Learning
Figure 4 for Doubly Mild Generalization for Offline Reinforcement Learning
Viaarxiv icon

Expanding Sparse Tuning for Low Memory Usage

Add code
Nov 04, 2024
Figure 1 for Expanding Sparse Tuning for Low Memory Usage
Figure 2 for Expanding Sparse Tuning for Low Memory Usage
Figure 3 for Expanding Sparse Tuning for Low Memory Usage
Figure 4 for Expanding Sparse Tuning for Low Memory Usage
Viaarxiv icon

Towards Dynamic Message Passing on Graphs

Add code
Oct 31, 2024
Viaarxiv icon