|
Seongwoong Cho xtjddndx [at] gmail.com I am a Deep Learning Research Engineer at Mobilint. My current research focuses on model optimization for efficient AI deployment, with a particular emphasis on quantization techniques. I am developing quantization algorithms that operate robustly under constrained environments—such as integer-only accelerators—and generalize well across various architectures, including Transformers and CNNs. More broadly, I am interested in developing data-efficient and generalizable AI systems. My prior work includes few-shot learning for out-of-distribution (OOD) tasks, where I explored methods that enable generalization across both novel tasks and domains. I remain enthusiastic about advancing a wide range of Machine Learning technologies, including Computer Vision, Natural Language Processing, and Reinforcement Learning. CV / Google Scholar / GitHub / LinkedIn |
|
News
Sep 2024: Meta-Controller was accepted to NeurIPS 2024. |
Research* denotes equal contribution. |
|
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
Seongwoong Cho*, Donggyun Kim*, Jinwoo Lee, Seunghoon Hong NeurIPS, 2024 paper / code |
|
Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild
Donggyun Kim, Seongwoong Cho, Semin Kim, Chong Luo, Seunghoon Hong ECCV, 2024 (Oral Presentation) paper / code |
|
Universal Few-shot Learning
of
Dense Prediction Tasks with Visual Token
Matching
Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong ICLR, 2023 (Outstanding Paper Award) paper / code |
|
Multi-task Neural processes
Donggyun Kim, Seongwoong Cho, Wonkwang Lee, Seunghoon Hong ICLR, 2022 paper / code |
Experience
Mobilint Inc.
Waddle Inc.
Pavilion Inc.
NCSOFT ASR Group |
Honors
Outstanding Paper Award, ICLR 2023
(as
a coauthor) |
|
Last updated: Sep 2024 |
Built from Jon Barron's academic website |