Sangdoo Yun

MASEval: Extending Multi-Agent Evaluation from Models to Systems ACL 2026 Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models ACL 2026 DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation ICLR 2025 Code-Switching Curriculum Learning for Multilingual Transfer in LLMs ACL 2025 Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025 Probabilistic Language-Image Pre-Training ICLR 2025 Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers EMNLP 2025 A Unified Framework for Motion Reasoning and Generation in Human Interaction ICCV 2025 Masking meets Supervision: A Strong Learning Alliance CVPR 2025 HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts ECCV 2024 Who Wrote this Code? Watermarking for Code Generation ACL 2024 Calibrating Large Language Models Using Their Generations Only ACL 2024 TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models ACL 2024 TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification ACL 2024 Toward Interactive Regional Understanding in Vision-Large Language Models NAACL 2024 Compressed Context Memory for Online Language Model Interaction ICLR 2024 Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models ICLR 2024 Towards Calibrated Robust Fine-Tuning of Vision-Language Models NIPS 2024 Language-only Training of Zero-shot Composed Image Retrieval CVPR 2024 Direct Unlearning Optimization for Robust and Safe Text-to-Image Models NIPS 2024 Rotary Position Embedding for Vision Transformer ECCV 2024 Model Stock: All we need is just a few fine-tuned models ECCV 2024 Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data NIPS 2023 MPCHAT: Towards Multimodal Persona-Grounded Conversation ACL 2023 SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage ICCV 2023 Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts ICCV 2023 Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models EMNLP 2023 Exploring Temporally Dynamic Data Augmentation for Video Recognition ICLR 2023 What Do Self-Supervised Vision Transformers Learn? ICLR 2023 ProPILE: Probing Privacy Leakage in Large Language Models NIPS 2023 The Majority Can Help the Minority: Context-Rich Minority Oversampling for Long-Tailed Classification CVPR 2022 A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective NIPS 2022 Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning CVPR 2022 Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data CVPR 2022 OCR-Free Document Understanding Transformer ECCV 2022 Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective ICLR 2022 Dataset Condensation via Efficient Synthetic-Data Parameterization ICML 2022 Dataset Condensation with Contrastive Signals ICML 2022 Rethinking Channel Dimensions for Efficient Model Design CVPR 2021 Rethinking Spatial Dimensions of Vision Transformers ICCV 2021 AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights ICLR 2021 Normalization Matters in Weakly Supervised Object Localization ICCV 2021 Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels CVPR 2021 Learning De-biased Representations with Biased Representations ICML 2020 What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis ICCV 2019 A Comprehensive Overhaul of Feature Distillation ICCV 2019 Character Region Awareness for Text Detection CVPR 2019 Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons AAAI 2019 Knowledge Distillation with Adversarial Samples Supporting Decision Boundary AAAI 2019 CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features ICCV 2019 Unsupervised holistic image generation from key local patches ECCV 2018 Context-Aware Deep Feature Compression for High-Speed Visual Tracking CVPR 2018 Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning CVPR 2017 Attentional Correlation Filter Network for Adaptive Visual Tracking CVPR 2017 Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold CVPR 2017 Visual Path Prediction in Complex Scenes With Crowded Moving Objects CVPR 2016