Huaxiaoyue (Yuki) Wang

PoRTaL lab member. 4th Year CS Ph.D. at Cornell University.

yuki_profile_pic.jpg

yukiwang at cs.cornell.edu

hw575 at cornell.edu

Hi! I am a final year CS PhD student at Cornell Univeristy. I am currently a member of the PoRTaL lab, working with Prof. Sanjiban Choudhury. For Summer 2025, I am a Research Intern at Adobe, working with Stefano Petrangeli on AI assistants for content creation.

I work on interactive AI agents that learn and act given different levels of information (e.g., goal specification, vague language feedback, few-shot video demonstrations).

My research focuses on LLM agents, imitation learning (IRL), and foundation models for robotics.

I did my undergrad at Harvey Mudd College, where I did research in a wide range of areas: human-robot interactions(@HEATlab), underwater robotics (@LAIR), and experimental airplane construction (@HMC Aero Lab).

Link to my CV!

News

Jul, 2025 📣 I am presenting our paper Imitation Learning from Temporally Misaligned Demonstrations at ICML 2025! I am also presenting The Road Not Taken: Hindsight Exploration for LLMs in Multi-Turn RL at the ES-FoMo III and the Exploration in AI Today workshop!
May, 2025 🌎 I am currently a Research Intern at Adobe, working with Stefano Petrangeli on AI assistants for content creation.
Jan, 2025 📝 A new paper on imitation learning from a single temporally misaligned video demonstration is available as a preprint! An earlier version was accepted to CoRL 2024 Workshop on Whole-body Control and Bimanual Manipulation: Applications in Humanoids and Beyond.
Nov, 2024 📣 I presented our papers APRICOT and MOSAIC at CoRL in Germany! Check out me giving a spotlight talk about APRICOT and Juntao presenting MOSAIC!
Sep, 2024 📝 Two first-authored papers accepted to CoRL 2024! APRICOT presents a novel algorithm that allows LLMs to systematically query users to reduce uncertainty, and MOSAIC showcases a multi-robot system that collaborates with users to cook!
May, 2024 🏆 My co-authored paper MOSAIC with Kushal Kedia and Juntao Ren won the best paper award at the VLNMN workshop and the best poster at the MoMa workshop at ICRA 2024!
Dec, 2023 📣 I presented our paper Demo2Code at NeurIPS 2023 in New Orleans! Check out our poster and video!
Sep, 2023 📝 My first paper Demo2Code on code generation given video demonstration got accepted to NeurIPS 2023!

Selected Publications

  1. Imitation Learning from a Single Temporally Misaligned Video
    William Huey*, Huaxiaoyue Wang*, Anne Wu, and 2 more authors
    2025
    arXiv Code
  2. APRICOT: Active Preference Learning and Constraint-Aware Task Planning with LLMs
    Huaxiaoyue Wang, Nathaniel Chin, Gonzalo Gonzalez-Pumariega, and 5 more authors
    In 8th Annual Conference on Robot Learning 2024
    arXiv Code Poster Website
  3. MOSAIC: Modular Foundation Models for Assistive and Interactive Cooking
    Huaxiaoyue Wang*, Kushal Kedia*, Juntao Ren*, and 14 more authors
    In 8th Annual Conference on Robot Learning 2024
    arXiv Poster Website
  4. Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought
    Huaxiaoyue Wang, Gonzalo Gonzalez-Pumariega, Yash Sharma, and 1 more author
    In Thirty-seventh Conference on Neural Information Processing Systems 2023
    arXiv Code Poster Website