I am a second-year Master’s student in Computer Science at the University of Bern. I received my Bachelor’s degree in Software Engineering from Xi’an Jiaotong University in China. My research interests lie in optimization algorithms in deep learning, Multi-task Learning based Multimodal Learning and its relevant applications, Reinforcement Learning and Generative Models.
A missing-modality multimodal fusion framework that preserves a modality-complete fusion interface by synthesizing proxy tokens for absent modalities in a shared latent space.
A plug-and-play geometry-aware regularization framework for multimodal learning, encouraging intra-modal dispersion and inter-modal anchoring to mitigate representation collapse and cross-modal drift.
A lightweight Kalman-filter-based reward estimation method for policy gradient reinforcement learning, replacing fixed reward normalization with online latent reward mean estimation to reduce variance and improve convergence.
An extension of KOALA, a neural network optimization algorithm based on Kalman filtering, with implicit full weights covariance matrix.