Sotabase

Career

· PhD Student, University of Oxford, Mobile Robotics Group (MRG)2024–

Publications (9)

SpatialBot: Precise Spatial Understanding with Vision Language Models
IEEE International Conference on Robotics and Automation · 2024
135
cited
Efficient Multimodal Learning from Data-centric Perspective
arXiv.org · 2024
125
cited
RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model
Robotics: Science and Systems · 2024
85
cited
Real-Fake: Effective Training Data Synthesis Through Distribution Matching
International Conference on Learning Representations · 2023
45
cited
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
Trans. Mach. Learn. Res. · 2024
18
cited
Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
International Conference on Machine Learning · 2022
17
cited
SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model
arXiv.org · 2024
14
cited
FlexiFilm: Long Video Generation with Flexible Conditions
arXiv.org · 2024
13
cited
LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
arXiv.org · 2025
3
cited
Sotabase
Jianhao Yuan | Researcher Profile | Sotabase | Sotabase