Sotabase

Career

· Research Scientist, xAI2024–
· Research Scientist, Google DeepMind2023–2024
· Research Scientist, Google Brain2021–2023
· PhD in Computer Science, University of Southern California2017–2021
· Ph.D. in Computer Science (Transfer), University of California, Los Angeles2016–2017
· Bachelor of Science in Computer Science, Simon Fraser University2013–2016
· Bachelor of Engineering in Computer Science and Technology, Zhejiang University2011–2013

Publications (53)

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions
Computer Vision and Pattern Recognition · 2018
779
cited
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
International Conference on Machine Learning · 2022
382
cited
Compressed Video Action Recognition
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
348
cited
Learning the Best Pooling Strategy for Visual Semantic Embedding
Computer Vision and Pattern Recognition · 2020
309
cited
PaLI-X: On Scaling up a Multilingual Vision and Language Model
arXiv.org · 2023
255
cited
Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition
Computer Vision and Pattern Recognition · 2015
249
cited
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Neural Information Processing Systems · 2019
244
cited
MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text
Conference on Empirical Methods in Natural Language Processing · 2022
244
cited
Subject-driven Text-to-Image Generation via Apprenticeship Learning
Neural Information Processing Systems · 2023
234
cited
Re-Imagen: Retrieval-Augmented Text-to-Image Generator
International Conference on Learning Representations · 2022
231
cited
Cross-Modal and Hierarchical Modeling of Video and Text
European Conference on Computer Vision · 2018
206
cited
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
arXiv.org · 2025
175
cited
Engaging Image Captioning via Personality
Computer Vision and Pattern Recognition · 2018
160
cited
Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
Conference on Empirical Methods in Natural Language Processing · 2023
158
cited
Learning Structured Inference Neural Networks with Label Relations
Computer Vision and Pattern Recognition · 2015
129
cited
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
IEEE International Conference on Computer Vision · 2023
94
cited
Learning Embedding Adaptation for Few-Shot Learning
arXiv.org · 2018
90
cited
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
Annual Meeting of the Association for Computational Linguistics · 2020
79
cited
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
Neural Information Processing Systems · 2023
78
cited
Instruct-Imagen: Image Generation with Multi-modal Instruction
Computer Vision and Pattern Recognition · 2024
76
cited
Sotabase
Hexiang Hu | Researcher Profile | Sotabase | Sotabase