11 papers
Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration
Beiwen Zhang, Yongheng Liang, Guowei Zou +2
Constructing efficient and reliable policies to assist humans is indispensable for human-AI collaboration. Existing methods mainly follow two lines of work. Most prior work relies…
Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation
Zhiquan Chen, Haitao Wang, Guowei Zou +1
Accurate medical image segmentation is fundamental to precision medicine, yet robust delineation remains challenging under heterogeneous appearances, ambiguous boundaries, and larg…
SpectraFlow: Unifying Structural Pretraining and Frequency Adaptation for Medical Image Segmentation
Zhiquan Chen, Haitao Wang, Guowei Zou +1
Medical image segmentation remains challenging in low-data regimes, where scarce annotations often yield poor generalization and ambiguous boundaries with missing fine structures.…
CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
Guowei Zou, Haitao Wang, Beiwen Zhang +2
How can generative offline multi-agent reinforcement learning achieve both fast joint trajectory generation and effective cooperation? Multi-agent diffusion models generate joint t…
CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments
Hong Hong, Feiyu Liao, Yongheng Liang +4
In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received less attention than obstacle number or density. Existing methods typ…
MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement Learning
Chenxing Lin, Xinhui Gao, Haipeng Zhang +7
Generative models have gained significant traction in offline reinforcement learning (RL) due to their ability to model complex trajectory distributions. However, existing generati…
OGPO: One-Step Generative Policy Optimization for Real-Time Robot Control
Guowei Zou, Haitao Wang, Hejun Wu +3
Real-time robot control demands fast action generation. Diffusion and flow matching policies for robot control require multi-step sampling, limiting their deployment in real-time s…
DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
Guowei Zou, Haitao Wang, Hejun Wu +3
The ability to learn multi-modal action distributions is indispensable for robotic manipulation policies to perform precise and robust control. Flow-based generative models have re…
PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork
Beiwen Zhang, Yongheng Liang, Guowei Zou +3
Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems. Existing ad hoc teamwork methods typically drive controlled…
D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss
Guowei Zou, Weibing Li, Hejun Wu +3
Diffusion policies excel at robotic manipulation by naturally modeling multimodal action distributions in high-dimensional spaces. Nevertheless, diffusion policies suffer from diff…
Asynchronous Credit Assignment for Multi-Agent Reinforcement Learning
Yongheng Liang, Hejun Wu, Haitao Wang +1
Credit assignment is a critical problem in multi-agent reinforcement learning (MARL), aiming to identify agents' marginal contributions for optimizing cooperative policies. Current…