MM-Gaussian: 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes

no code implementations • 5 Apr 2024 • Chenyang Wu, Yifan Duan, Xinran Zhang, Yu Sheng, Jianmin Ji, Yanyong Zhang

In this work, we present MM-Gaussian, a LiDAR-camera multi-modal fusion system for localization and mapping in unbounded scenes.

Autonomous Vehicles

Reinforced In-Context Black-Box Optimization

1 code implementation • 27 Feb 2024 • Lei Song, Chenxiao Gao, Ke Xue, Chenyang Wu, Dong Li, Jianye Hao, Zongzhang Zhang, Chao Qian

In this paper, we propose RIBBO, a method to reinforce-learn a BBO algorithm from offline data in an end-to-end fashion.

In-Context Learning Meta-Learning

ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning

1 code implementation • 12 Sep 2023 • Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Rui Kong, Zongzhang Zhang, Yang Yu

Third, we train an Advantage-Conditioned Transformer (ACT) to generate actions conditioned on the estimated advantages.

Action Generation

Adaptive Online Packing-guided Search for POMDPs

1 code implementation • NeurIPS 2021 • Chenyang Wu, Guoyu Yang, Zongzhang Zhang, Yang Yu, Dong Li, Wulong Liu, Jianye Hao

A belief is a distribution of states representing state uncertainty.