Sotabase

Career

· Researcher, Meta AI / Meta Superintelligence Labs2023–
· PhD Student, University of Oxford, Torr Vision Group2023–

Publications (30)

Dual Contrastive Learning for Unsupervised Image-to-Image Translation
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2021
192
cited
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
arXiv.org · 2023
104
cited
Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
Remote Sensing · 2021
95
cited
3D-GPT: Procedural 3D Modeling with Large Language Models
International Conference on 3D Vision · 2023
73
cited
Single Underwater Image Restoration by Contrastive Learning
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS · 2021
56
cited
VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
European Conference on Computer Vision · 2024
53
cited
Blind Image Decomposition
European Conference on Computer Vision · 2021
47
cited
You Only Cut Once: Boosting Data Augmentation with a Single Cut
International Conference on Machine Learning · 2022
35
cited
Hyperbolic Audio-visual Zero-shot Learning
IEEE International Conference on Computer Vision · 2023
24
cited
GOSS: towards generalized open-set semantic segmentation
The Visual Computer · 2022
21
cited
Curved Geometric Networks for Visual Anomaly Recognition
IEEE Transactions on Neural Networks and Learning Systems · 2022
19
cited
CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping
arXiv.org · 2022
10
cited
Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
Computer Vision and Pattern Recognition · 2025
10
cited
VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models
arXiv.org · 2025
10
cited
Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation
International Conference on Machine Learning · 2024
8
cited
NeRFEditor: Differentiable Style Decomposition for 3D Scene Editing
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2024
8
cited
NeRFEditor: Differentiable Style Decomposition for Full 3D Scene Editing
arXiv.org · 2022
7
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
What Images are More Memorable to Machines?
arXiv.org · 2022
5
cited
Sotabase
Junlin Han | Researcher Profile | Sotabase | Sotabase