yang-su2000 / voice2action

Implemetation of paper and Unity package "Voice2Action: Language Models as Agent for Efficient Real-Time Interaction in VR".

Welcome to Yang's GitHub

Hi there! I am an MS student from Cornell, focusing on efficient, scalable language modeling and agent systems.

I am happy to chat and discuss potential collaborations, feel free to reach out by

🌟 Studying Zone

I am collaborating with Cornell ICPC and Millennium to build efficient LLMs for code and data generation in interactive environments.

• This work is called ALICE (Aligning Language models for Interactive Code Execution), you can find more about it in this Google Slide.
• ALICE aims to build actually usable (i.e. low-cost, efficient) code generation system in large-scale interactive environments.
• We are currently experimenting the physics engine environment due to its simulation and feedback loop flexibility.
• ALICE is expected to expand to other domains like robotics simulation, VR, autonomous driving, etc.
• Borader Impact: ALICE can generate high-quality synthetic data with active human intervention, for training LLMs.

We are actively looking for brilliant people to join the ALICE project, shoot me an email if you are interested!

Previously, I led the prior work of ALICE called Voice2Action with Cornell XRC, an Unity Package for real-time code execution in VR.

I am also working on large-scale generation augmented retrieval systems (opposed to RAG) at Cornell NLP.

I used to work on graph machine learning at AWS AI Lab (2021-2022) and contribute to the open source Deep Graph Library.

👀 Chilling Zone

I like programming! I lead the "Cornell Tech" Group at Cornell ICPC and won the Top 20% in 2023 Regional!

I enjoy cooking, listening to music of all forms, playing ping-pong, reading science fiction, and more!

⚡ Developing Zone

📈 "Accepted" Zone