6 citations · 23 across the 31 of their papers we have counts for
32 papers
NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation
Yumeng He, Eachen Soong, Yichen Song +6
The advancement of Embodied AI necessitates high-quality simulation assets that faithfully mirror the real world. However, transforming raw visual observations into simulation-read…
LASER: Learning Active Sensing for Continuum Field Reconstruction
Huayu Deng, Jinghui Zhong, Xiangming Zhu +2
High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. C…
Unicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling
Haochen Yuan, Yichen Song, Yunbo Wang +1
Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical inter-channel dependencies, whi…
OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence
Jiajian Li, Jingyuan Huang, Junru Gong +3
We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence. Unlike prior world models th…
EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
Yumeng He, Zanwei Zhou, Yekun Zheng +3
Volume electron microscopy (vEM) enables nanoscale 3D imaging of biological structures but remains constrained by acquisition trade-offs, leading to anisotropic volumes with limite…
Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
Qi Wang, Mian Wu, Yuyang Zhang +7
Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Des…
NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding
Yanpeng Zhao, Shanyan Guan, Yunbo Wang +3
We introduce NeoWorld, a deep learning framework for generating interactive 3D virtual worlds from a single input image. Inspired by the on-demand worldbuilding concept in the scie…
Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization
Haochen Yuan, Minting Pan, Yunbo Wang +3
Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns…
Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
Minting Pan, Yitao Zheng, Jiajian Li +2
Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with…
Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
Mingqi Yuan, Qi Wang, Guozheng Ma +8
Developing lifelong learning agents is crucial for artificial general intelligence (AGI). However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where…
Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
Qi Wang, Zhipeng Zhang, Baao Xie +6
Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, RL agents suffer from low sample efficiency in environments wi…
DimINO: Dimension-Informed Neural Operator Learning
Yichen Song, Yalun Wu, Yunbo Wang +1
In computational physics, a longstanding challenge lies in finding numerical solutions to partial differential equations (PDEs). Recently, research attention has increasingly focus…
EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions
Huayu Deng, Xiangming Zhu, Yunbo Wang +1
Graph neural networks have been a powerful tool for mesh-based physical simulation. To efficiently model large-scale systems, existing methods mainly employ hierarchical graph stru…
Open-World Reinforcement Learning over Long Short-Term Imagination
Jiajian Li, Qi Wang, Yunbo Wang +4
Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by…
ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting
Haochen Yuan, Yutong Wang, Yihong Chen +2
Time series forecasting, particularly in few-shot learning scenarios, is challenging due to the limited availability of high-quality training data. To address this, we present a pi…
Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering
Yanpeng Zhao, Yiwei Hao, Siyu Gao +2
Learning object-centric representations from unsupervised videos is challenging. Unlike most previous approaches that focus on decomposing 2D images, we present a 3D generative mod…
Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video
Xiangming Zhu, Huayu Deng, Haochen Yuan +2
We introduce latent intuitive physics, a transfer learning framework for physics simulation that can infer hidden properties of fluids from a single 3D video and simulate the obser…
MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting
Yumeng He, Yunbo Wang, Xiaokang Yang
Out-of-distribution (OOD) 3D relighting requires novel view synthesis under unseen lighting conditions that differ significantly from the observed images. Existing relighting metho…
Model-Based Reinforcement Learning with Multi-Task Offline Pretraining
Minting Pan, Yitao Zheng, Yunbo Wang +1
Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mism…
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Qi Wang, Junming Yang, Yunbo Wang +3
Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected f…
DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
Yanpeng Zhao, Siyu Gao, Yunbo Wang +1
Unsupervised learning of object-centric representations in dynamic visual scenes is challenging. Unlike most previous approaches that learn to decompose 2D images, we present DynaV…
Model-Based Reinforcement Learning with Isolated Imaginations
Minting Pan, Xiangming Zhu, Yitao Zheng +2
World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are indep…
Improving Masked Autoencoders by Learning Where to Mask
Haijian Chen, Wendong Zhang, Yunbo Wang +1
Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variatio…
Continual Visual Reinforcement Learning with A Life-Long World Model
Minting Pan, Wendong Zhang, Geng Chen +4
Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requi…