Dongyoon Han

Exploring Conditions for Diffusion Models in Robotic Control CVPR 2026 MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model CVPR 2026 StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation ACL 2026 Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models CVPR 2026 DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation ICLR 2025 Masking meets Supervision: A Strong Learning Alliance CVPR 2025 Morphing Tokens Draw Strong Masked Image Models ICLR 2025 NegMerge: Sign-Consensual Weight Merging for Machine Unlearning ICML 2025 Peri-LN: Revisiting Normalization Layer in the Transformer Architecture ICML 2025 Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models ICLR 2025 DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs ECCV 2024 HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts ECCV 2024 Learning with Unmasked Tokens Drives Stronger Vision Learners ECCV 2024 Leveraging temporal contextualization for video action recognition ECCV 2024 Model Stock: All we need is just a few fine-tuned models ECCV 2024 Rotary Position Embedding for Vision Transformer ECCV 2024 SeiT++: Masked Token Modeling Improves Storage-efficient Training ECCV 2024 Similarity of Neural Architectures using Adversarial Attack Transferability ECCV 2024 Towards Calibrated Robust Fine-Tuning of Vision-Language Models NeurIPS 2024 Can We Find Strong Lottery Tickets in Generative Models? AAAI 2023 Frequency Selective Augmentation for Video Representation Learning AAAI 2023 GeNAS: Neural Architecture Search with Better Generalization IJCAI 2023 Generating Instance-level Prompts for Rehearsal-free Continual Learning ICCV 2023 Gramian Attention Heads are Strong yet Efficient Vision Learners ICCV 2023 Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts ICCV 2023 Scratching Visual Transformer's Back with Uniform Attention ICCV 2023 Switching Temporary Teachers for Semi-Supervised Semantic Segmentation NeurIPS 2023 The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation CVPR 2023 Contrastive Vicinal Space for Unsupervised Domain Adaptation ECCV 2022 Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training? CVPR 2022 Learning Features with Parameter-Free Layers ICLR 2022 OCR-Free Document Understanding Transformer ECCV 2022 Time Is MattEr: Temporal Self-supervision for Video Transformers ICML 2022 ViDT: An Efficient and Effective Fully Transformer-based Object Detector ICLR 2022 AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights ICLR 2021 Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels CVPR 2021 Rethinking Channel Dimensions for Efficient Model Design CVPR 2021 Rethinking Spatial Dimensions of Vision Transformers ICCV 2021 Character Region Awareness for Text Detection CVPR 2019 CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features ICCV 2019 What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis ICCV 2019 Deep Pyramidal Residual Networks CVPR 2017 Unsupervised Simultaneous Orthogonal Basis Clustering Feature Selection CVPR 2015 Salient Region Detection via High-Dimensional Color Transform CVPR 2014