Research

My general research interests lie in multimodal fusion and embodied intelligence and deep resnet reinforcement learning, with a particular emphasis on the following topics:

• Theory:
  Analysis and understandings of the generalization ability of multimodal loss functions.

• Algorithm:
  Development of effective deep learning algorithms for robotic multimodal fusion and resnet reinforcement learning.

• Application:
  Application of learning algorithms in embodied intelligence, assembly, and human-robot contact rich manipulation.

Feel free to drop me an email if you are interested in collaborating with me on the above research topics.

---

Publications

(* Corresponding author; † Equal contribution)

• Ruoxuan Feng, Jiangyu Hu, Wenke Xia, Tianci Gao, Ao Shen, Yuhao Sun, Bin Fang, Di Hu.
  AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors.
  The Thirteenth International Conference on Learning Representations (ICLR).
  

• Jiangyu Hu, Huasong Min.
  XR Interface to Enhance the Learning Feeling in Arc Welding Training Tasks.
  43rd Chinese Control Conference (CCC).
  

• Jiangyu Hu, Huasong Min.
  QwenGrasp: A Usage of Large Vision Language Model for Target-oriented Grasping.
  2024 Chinese Control Conference (CAC).
  

• Jiangyu Hu, Huasong Min.
  Neural contact fields: Tracking extrinsic contact with tactile sensing.
  2024 IEEE International Conference on Robotics and Biomimetics (ROBIO).
  

• Jiangyu Hu, Huasong Min.
  Tac-VGNN: A Voronoi Graph Neural Network for Pose-Based Tactile Servoing.
  2024 IEEE International Conference on Robotics and Biomimetics (ROBIO).
  

• Jiangyu Hu, Huasong Min.
  A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutters.
  The 5th China Intelligent Robotics Academic Conference (CIRAC).
  

• Jiangyu Hu, Huasong Min.
  Octopi: Object Property Reasoning with Large Tactile-Language Models.
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).