Awesome Computer Vision
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
← authors
·
overview
Sewoong Oh
15
papers ·
45
citations ·
37
h-index
University of Washington · Seattle University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Privacy-preserving Instructions For Aligning Large Language Models
2024 · 41 citations
DataComp-LM: In search of the next generation of training sets for language models
2024 · 3 citations
DPZero: Private Fine-Tuning of Language Models without Backpropagation
2023 · 1 citations
DataComp-VLM: Improved Open Datasets for Vision-Language Models
2026
Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model
2026
DataComp-VLM: Improved Open Datasets for Vision-Language Models
2026
Are Robust LLM Fingerprints Adversarially Robust?
2025
Open Deep Search: Democratizing Search with Open-source Reasoning Agents
2025
Concept-Aware Batch Sampling Improves Language-Image Pretraining
2025
Understanding The Gain From Data Filtering In Multimodal Contrastive Learning
2025
Top-$K$ Ranking from Pairwise Comparisons: When Spectral Ranking is Optimal
2016
Deepcode: Feedback Codes via Deep Learning
2018
LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks
2018
AirGapAgent: Protecting Privacy-Conscious Conversational Agents
2024
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
2024
Topics
Training Techniques
Evaluation
Safety & Alignment
Vision-Language
Efficiency
data
Fine-Tuning
Vision-Language Models
Agentic
Model Architecture
Sewoong Oh — most-cited papers & profile · Computer Vision