Yiyang Ling

I am a first year PhD student in Computer Science at University of Southern California, advised by Prof. Daniel Seita. I received my Bachelor's degree at ACM Honors Class, Shanghai Jiao Tong University.

My research interest lies in robot learning. Previously, I worked as a student intern at University of California San Diego, under the supervision of Prof. Xiaolong Wang. Before this, I gained valuable experience as a research assistant in the SJTU Machine Vision and Intelligence Group, where I was advised by Prof. Cewu Lu.

Email  /  GitHub  /  Google Scholar  /  Twitter  

Research

GenSim: Generating Robotic Simulation Tasks via Large Language Models

In this work, we propose to automatically generate rich simulation environments and expert demonstrations by exploiting LLMs’ grounding and coding ability. Our approach has two modes: goal-directed generation, wherein LLM proposes a task curriculum to solve a target task, and exploratory generation, wherein LLM bootstraps from previous tasks and iteratively proposes novel complex tasks.

TC-CNE: Scalable Tensorized Contrastive Cross-Network Embedding

We propose a scalable tensorized cross-network embedding method based on contrastive learning by introducing the utilization of CP Decomposition and intra/inter-network sub-embeddings. We achieve to save storage space and accelerate embedding learning simultaneously in a unified training pipeline.

Design and source code from Leonid Keselman's website