9 papers
FastPano3D: Feed-Forward Indoor Panoramic 3D Reconstruction from a Single Image
Jianqiang Li, Liumei Zhang, Wenjia Guo +5
Recent advances in 3D scene reconstruction have highlighted the intricate trade-offs among rendering quality, inference efficiency, and data dependency. To address the challenge of…
Gradient Leakage Defense with Key-Lock Module for Federated Learning
Hanchi Ren, Jingjing Deng, Xianghua Xie
Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local mo…
From Local Patterns to Global Understanding: Cross-Stock Trend Integration for Enhanced Predictive Modeling
Yi Hu, Hanchi Ren, Jingjing Deng +1
Stock price prediction is a critical area of financial forecasting, traditionally approached by training models using the historical price data of individual stocks. While these mo…
Triplane Grasping: Efficient 6-DoF Grasping with Single RGB Images
Yiming Li, Hanchi Ren, Yue Yang +2
Reliable object grasping is one of the fundamental tasks in robotics. However, determining grasping pose based on single-image input has long been a challenge due to limited visual…
Task-oriented Robotic Manipulation with Vision Language Models
Nurhan Bulus Guran, Hanchi Ren, Jingjing Deng +1
Vision Language Models (VLMs) play a crucial role in robotic manipulation by enabling robots to understand and interpret the visual properties of objects and their surroundings, al…
FissionVAE: Federated Non-IID Image Generation with Latent Space and Decoder Decomposition
Chen Hu, Hanchi Ren, Jingjing Deng +2
Federated learning is a machine learning paradigm that enables decentralized clients to collaboratively learn a shared model while keeping all the training data local. While consid…