Dongyoon Han
- Papers
- 37
Cite
Notes
Only stored in your browser.
Authored papers
37Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
arXiv 2026
Grounding World Simulation Models in a Real-World Metropolis
arXiv 2026
On the Reliability of Cue Conflict and Beyond
arXiv 2026
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
arXiv 2025
Token Bottleneck: One Token to Remember Dynamics
arXiv 2025
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
arXiv 2024
Rotary Position Embedding for Vision Transformer
arXiv 2024
Leveraging Temporal Contextualization for Video Action Recognition
arXiv 2024
Model Stock: All we need is just a few fine-tuned models
arXiv 2024
HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
arXiv 2024
MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
arXiv 2024
DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
arXiv 2024
Tint Your Models Task-wise for Improved Multi-task Model Merging
arXiv 2024
NegMerge: Consensual Weight Negation for Strong Machine Unlearning
arXiv 2024
Masking meets Supervision: A Strong Learning Alliance
CVPR 2025 1
Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
arXiv 2023
The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation
CVPR 2023 1
SeiT++: Masked Token Modeling Improves Storage-efficient Training
arXiv 2023
GeNAS: Neural Architecture Search with Better Generalization
arXiv 2023
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
arXiv 2023
Learning with Unmasked Tokens Drives Stronger Vision Learners
arXiv 2023
Morphing Tokens Draw Strong Masked Image Models
arXiv 2023
Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images
arXiv 2023
An Extendable, Efficient and Effective Transformer-based Object Detector
arXiv 2022
Time Is MattEr: Temporal Self-supervision for Video Transformers
arXiv 2022
Learning Features with Parameter-Free Layers
learning-features-with-parameter-free-layers
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?
CVPR 2022 1
OCR-free Document Understanding Transformer
arXiv 2021
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
CVPR 2021 1
Rethinking Spatial Dimensions of Vision Transformers
ICCV 2021 10
Contrastive Vicinal Space for Unsupervised Domain Adaptation
arXiv 2021
Rethinking Channel Dimensions for Efficient Model Design
CVPR 2021 1
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
adamp-slowing-down-the-slowdown-for-momentum
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
what-is-wrong-with-scene-text-recognition-1
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
cutmix-regularization-strategy-to-train-1
EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
arXiv 2019
Deep Pyramidal Residual Networks
deep-pyramidal-residual-networks-1
Affiliations
Frequent co-authors
10from 37 papers