Dokwan Oh
9 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (18)
π
Cross-Pollinator
(6)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
ICML (3)
NIPS (3)
CVPR (1)
ECCV (1)
EMNLP (1)
Top co-authors
Keywords
semantic segmentation
(2)
self-supervised learning
(2)
model compression
(2)
representation learning
(1)
image segmentation
(1)
attention mechanism
(1)
knowledge distillation
(1)
unsupervised domain adaptation
(1)
context modeling
(1)
deep model
(1)
implicit neural representation
(1)
convolutional neural network
(1)
post-training compression
(1)
video representation
(1)
multi-scale attention
(1)
class probability
(1)
auxiliary loss
(1)
strong lottery ticket hypothesis
(1)
diffeomorphic transformation
(1)
sequence length
(1)
Papers
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
ICML 2025
Beyond Fixed-Length Calibration for Post-Training Compression of LLMs
EMNLP 2025
Efficient Neural Video Representation with Temporally Coherent Modulation
ECCV 2024
Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
NIPS 2024
Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
ICML 2024
Is Overfitting Necessary for Implicit Video Representation?
ICML 2023
SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information
CVPR 2022
DaDA: Distortion-aware Domain Adaptation for Unsupervised Semantic Segmentation
NIPS 2022
Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly
NIPS 2021