Visual Test-time Scaling for GUI Agent Grounding (ICCV2025)
Probing Visual Language Priors in VLMs (ICML2025)
Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents (CVPR2025)
View Selection for 3D Captioning via Diffusion Ranking (ECCV2024)
Scalable 3D Captioning with Pretrained Models (NIPS2023)
A Unified Framework for Transforming between Text, Point Cloud, and Program (TMLR2023)
Universal Shape Templates Induction (NOTE2021)
A Bottom-Up Framework for 3D Part Discovery in Unseen Categories (ICLR2020)
Few-Shot Learning with Global Class Representations (ICCV2019)
Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy (CVPR2019)
Learning to Navigate for Fine-grained Classification (ECCV2018)
Research Experience
Published papers in top international conferences such as ICCV, ICML, CVPR, ECCV, NIPS, TMLR, and participated in multiple research projects.
Education
PhD student under Honglak Lee and Justin Johnson; Master's degree supervised by Liwei Wang.
Background
Research interests: machine learning, perception, multimodality, and reinforcement learning.
Miscellany
Reviewer for NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, AAAI, JMLR, TMLR, DMLR, TPAMI, AISTATS, RLC. Personal motto or hobby: Looking up at the Starry Sky. To be an expert, a beginner, and a storyteller.