Scholar
Songlin Wei
Google Scholar ID: jmtAxTgAAAAJ
University of Southern California, (Previously) Peking University
Citations & Impact
Citations
167
H-index
7
i10-index
6
Publications
12
Co-authors
0
Publications
Resume
Academic Achievements
- Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks, Arxiv Preprint, 2024
- RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments, Arxiv Preprint, 2024
- GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation, Arxiv Preprint, 2024
- D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation, CoRL 2024, Wild3D@ECCV 2024, 2024
- Make a Donut🍩: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools, Arxiv, 2024
- Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach, IROS, 2024
- SAGE🌿: Bridging Semantic and Actionable Parts for Generalizable Manipulation of Articulated Objects, RSS, 2024
- FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimation, Arxiv, 2023
Research Experience
- Developed large social media websites, built robots, and started companies. Finally found passion in research at Soochow University.
Background
- Research interests include 3D computer vision, robotic learning, and embodied AI. Currently working on Vision-Language-Action models for robotics.