Publications (12)
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…
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Baochang Ren, Xinjie Liu, Xi Chen +15
Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read lit…
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…
Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models
Minting Pan, Xiangming Zhu, Yunbo Wang +1
World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios such as autonomous driving, there commonly exists noncontrollabl…
ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions
Zhe Liu, Jiaming Gu, Zhaohui Du +7
Biological wet-lab protocols are written for trained researchers and often leave routine operations, state-dependent conditions, and contextual parameters implicit, making them dif…
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…
LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory
Jianbao Cao, Zhangrui Zhao, Bohan Feng +15
Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments.…
BioVLN: A Simulation Platform for Visual Language Navigation in Biomedical Laboratories
Zhe Liu, Quan Lu, Zhaohui Du +7
The paper presents BioVLN, a simulation platform that enables visual‑language navigation agents to safely approach biomedical laboratory instruments by modeling each instrument wit…
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…
Pipette: An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics
Zhe Liu, Huanbo Jin, Zhaohui Du +10
Pipette is an embodied simulation platform that provides open-source wet‑lab assets, a benchmark of 12 robotic tasks, and a data‑efficient augmentation pipeline to turn a few human…
BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
Zhaohui Du, Zhe Wang, Dongzhan Zhou +9
Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environments remains challenging. Protoco…
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…