Embodied navigation · 3D vision · agent systems
I am a Ph.D. student at Zhejiang University, supervised by Sida Peng and Xiaowei Zhou. My work centers on embodied navigation and 3D vision, with an emphasis on moving research systems into real-world use.
I am currently a research intern at OneRobotics's Artificial Intelligence Research Institute in Hangzhou. Outside research, I build open-source tools for agent collaboration and developer workflows.
Previously, I received my B.Eng. in Computer Science from Northwestern Polytechnical University, advised by Jiaqi Yang.
ICCV 2025
We present BoxDreamer, a novel framework that estimates 6-DoF object poses by predicting 3D bounding box corners from a single RGB image. Our approach achieves strong generalization to unseen object categories without requiring CAD models or category-specific training, enabling real-world deployment across diverse scenarios.
ECCV 2026
We introduce Habitat-GS, a photorealistic navigation simulator that replaces the mesh-based renderer of Habitat with a CUDA 3D Gaussian Splatting rasterizer and dynamic avatar modules, while staying compatible with the Habitat ecosystem so embodied agents can train and evaluate on visually realistic navigation tasks.
arXiv 2026
We propose EARTalking, a novel end-to-end, GPT-style autoregressive model for interactive audio-driven talking head generation. Our method introduces a frame-by-frame, in-context, audio-driven streaming generation paradigm with Sink Frame Window Attention for variable-length video generation with identity consistency.
I build practical tools for understanding agent behavior and coordinating AI-assisted work. These are the two projects that best represent that direction today.
Developer identity
Turns coding conversations into a visual developer portrait, surfacing working style, communication patterns, and technical preferences.
Agent collaboration
A practical collaboration protocol for agent-heavy projects, with handoffs, checkpoints, shared project state, and Feishu automation.