Sotabase

Career

· Research Intern, Snap Inc.2025–
· DPhil Student, University of Oxford2024–

Publications (13)

CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor
Computer Vision and Pattern Recognition · 2023
58
cited
Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation
International Conference on Learning Representations · 2024
23
cited
VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
arXiv.org · 2025
22
cited
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
Trans. Mach. Learn. Res. · 2024
18
cited
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages
Conference on Empirical Methods in Natural Language Processing · 2024
16
cited
OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
IEEE International Conference on Computer Vision · 2023
16
cited
Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
Computer Vision and Pattern Recognition · 2025
10
cited
Semantic Score Distillation Sampling for Compositional Text-to-3D Generation
arXiv.org · 2024
7
cited
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
International Conference on 3D Vision · 2024
6
cited
Label Alignment Regularization for Distribution Shift
Journal of machine learning research · 2022
2
cited
Reliable and Responsible Foundation Models
Trans. Mach. Learn. Res. · 2025
1
cited
EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
arXiv.org · 2025
Sotabase
Runjia Li | Researcher Profile | Sotabase | Sotabase