Publications (16)
Thinking Before You Speak: A Proactive Test-time Scaling Approach
Cong Liu, Wenchang Chai, Hejun Wu +3
Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and thos…
Cross-Modal Attentional Context Learning for RGB-D Object Detection
Guanbin Li, Yukang Gan, Hejun Wu +2
Recognizing objects from simultaneously sensed photometric (RGB) and depth channels is a fundamental yet practical problem in many machine vision applications such as robot graspin…
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…
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…
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…
Multi-party Agent Relation Sampling for Multi-party Ad Hoc Teamwork
Beiwen Zhang, Yongheng Liang, Hejun Wu
Multi-agent reinforcement learning (MARl) has achieved strong results in cooperative tasks but typically assumes fixed, fully controlled teams. Ad hoc teamwork (AHT) relaxes this b…
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…
CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
Guowei Zou, Haitao Wang, Beiwen Zhang +2
Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent…
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…
AMMASurv: Asymmetrical Multi-Modal Attention for Accurate Survival Analysis with Whole Slide Images and Gene Expression Data
Ruoqi Wang, Ziwang Huang, Haitao Wang +1
The use of multi-modal data such as the combination of whole slide images (WSIs) and gene expression data for survival analysis can lead to more accurate survival predictions. Prev…
One Step Is Enough: Dispersive MeanFlow Policy Optimization
Guowei Zou, Haitao Wang, Hejun Wu +3
Real-time robotic control demands fast action generation. However, existing generative policies based on diffusion and flow matching require multi-step sampling, fundamentally limi…
LRSVRG-IMC: An SVRG-Based Algorithm for LowRank Inductive Matrix Completion
Shangrong Yu, Yuxin Chen, Hejun Wu
Low-rank inductive matrix completion (IMC) is currently widely used in IoT data completion, recommendation systems, and so on, as the side information in IMC has demonstrated great…
Triangle Extension: Efficient Localizability Detection in Wireless Sensor Networks
Hejun Wu, Ao Ding, Lvzhou Li
Determining whether nodes can be localized, called localizability detection, is essential for wireless sensor networks (WSNs). This step is required for localizing nodes, achieving…
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.…
VisRec: A Semi-Supervised Approach to Radio Interferometric Data Reconstruction
Ruoqi Wang, Haitao Wang, Qiong Luo +2
Radio telescopes produce visibility data about celestial objects, but these data are sparse and noisy. As a result, images created on raw visibility data are of low quality. Recent…
CaMeRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments
Hong Hong, Feiyu Liao, Yongheng Liang +3
In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received strangely less attention than obstacle number or density. Existing m…