- MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents, NeurIPS 2025 Datasets and Benchmarks Track
- Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2025
- NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
- Correctable Landmark Discovery via Large Models for Vision-Language Navigation, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
- EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning, In submission to TPAMI; Under review
- PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly, NeurIPS 2025 Datasets and Benchmarks Track
- Awards:
- First Class Award Scholarship of the Graduate School, Sun Yat-sen University, in 2024, 2025
- Excellent Bachelor Dissertation Award of Sun Yat-sen University, in 2024 (Top 1 Recommended)
- Third Class Award Scholarship of Sun Yat-sen University Excellent Student, in 2020-2021, 2021-2022, and 2022-2023
Research Experience
- Research Intern, Huawei Noah’s Ark Lab, 2025.04-2025.12
- Data Engineering Intern, Tencent SSV ForGood Labs, 2023.07-2023.11
Education
- 09/2024 ~ 06/2027 (Expected): School of Intelligent Systems Engineering, Sun Yat-sen University, M.Eng. in Control Science and Engineering, Advisor: Prof. Xiaodan Liang, Weighted Average Score: 91.74/100.0
- 09/2020 ~ 06/2024: School of Intelligent Systems Engineering, Sun Yat-sen University, B.Sc. in Intelligent Science and Technology, GPA: 4.03/5.0, Ranking: 3/226, Top 1%
Background
- Research Interests: Multi-modal understanding, learning and data generation, Embodied AI, Spatial Intelligence, and Embodied generalist agents
- Field: Intelligent Science and Technology
- Introduction: Currently a second-year master's student at Sun Yat-sen University (SYSU) in the Human Cyber Physical Intelligence Integration Lab (HCP-I2 Lab), advised by Prof. Xiaodan Liang and Dr. Bingqian Lin.