Publications
Z. Li, Y. Ling, Y. Gu, B. Huang, C. Liang, S. Islam, H. Bedri, J. Chirikjian, Y. Li, S. Nikolaidis, D. Seita. “FELT: Generating Tactile Signals from Vision for Visuo-Tactile Manipulation.” Under review at ICRA 2027.
Predicts tactile signals from RGB images, enabling tactile augmentation of vision-only robot demonstrations. The synthesized tactile representations improve contact-rich manipulation without requiring physical tactile sensors at deployment.
RGB observations (top) and FELT-synthesized tactile signals (bottom).
H. Li, Z. Lin, Z. Qiu, Z. Li, H. Fu, Y. Hu, J. Liu. “Enhancing and Adapting in the Clinic: Source-Free Unsupervised Domain Adaptation for Medical Image Enhancement.” IEEE Transactions on Medical Imaging (TMI), 2024.
Adapts medical image enhancement models to unlabeled clinical data through source-free teacher–student learning while preserving anatomical structure.
Y. Lin, H. Li, H. Liu, H. Shu, Z. Li, Y. Hu, J. Liu. “Domain Adaptative Retinal Image Quality Assessment with Knowledge Distillation Using Competitive Teacher-Student Network.” IEEE ISBI, 2023.
Adapts retinal image quality assessment across domains through competitive teacher–student learning with target-specific pseudo-labels.
Experience
Graduate Research Assistant · SLURM Lab, USC
2025 – PresentResearching visuo-tactile perception for robotic manipulation; lead author on FELT.
Research Assistant · SUSTech
2022 – 2024Medical image enhancement and quality assessment (ISBI 2023, TMI 2024).
Research Intern · HiDream, Beijing
2023 – 2024Reproduced and adapted diffusion-based image super-resolution methods, studying how model changes and latent-noise settings affect image quality and detail.
About
I'm a CS master's student at USC researching visuo-tactile perception and robot learning at the SLURM Lab. I'm interested in how robots can infer contact from vision and use it to interact more effectively with the physical world.
Before USC, I studied at SUSTech, where I worked on medical image enhancement, domain adaptation, and image quality assessment. I also interned at HiDream, developing diffusion-based image restoration methods. Outside of research, I enjoy photography.