Sangdoo Yun

31

Papers

484

Total Citations

Papers (31)

Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models

Model Stock: All we need is just a few fine-tuned models

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

Masking meets Supervision: A Strong Learning Alliance

A Unified Framework for Motion Reasoning and Generation in Human Interaction

C-SEO Bench: Does Conversational SEO Work?

NeurIPS 2025arXiv

Token Bottleneck: One Token to Remember Dynamics

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

The Majority Can Help the Minority: Context-Rich Minority Oversampling for Long-Tailed Classification

Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning

Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data

A Comprehensive Overhaul of Feature Distillation

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Normalization Matters in Weakly Supervised Object Localization

Rethinking Spatial Dimensions of Vision Transformers

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts

OCR-Free Document Understanding Transformer

Rethinking Channel Dimensions for Efficient Model Design

Language-only Training of Zero-shot Composed Image Retrieval

Visual Path Prediction in Complex Scenes With Crowded Moving Objects

Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning

Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold

Attentional Correlation Filter Network for Adaptive Visual Tracking

Context-Aware Deep Feature Compression for High-Speed Visual Tracking

Character Region Awareness for Text Detection

A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective

ProPILE: Probing Privacy Leakage in Large Language Models

Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data