0

Sangdoo Yun

Papers
43

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
43papers

Authored papers

43

Grounding World Simulation Models in a Real-World Metropolis

arXiv 2026

2026

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction

arXiv 2026

2026

MEME: Multi-entity & Evolving Memory Evaluation

arXiv 2026

2026

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

arXiv 2026

2026

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

arXiv 2025

2025

Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation

arXiv 2025

2025

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

arXiv 2025

2025

LongProLIP: A Probabilistic Vision-Language Model with Long Context Text

arXiv 2025

2025

Token Bottleneck: One Token to Remember Dynamics

arXiv 2025

2025

Dr.LLM: Dynamic Layer Routing in LLMs

arXiv 2025

2025

Rotary Position Embedding for Vision Transformer

arXiv 2024

2024

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

arXiv 2024

2024

Calibrating Large Language Models Using Their Generations Only

arXiv 2024

2024

HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts

arXiv 2024

2024

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

arXiv 2024

2024

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

arXiv 2024

2024

Large-Scale Targeted Cause Discovery with Data-Driven Learning

arXiv 2024

2024

TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models

arXiv 2024

2024

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

arXiv 2024

2024

What Do Self-Supervised Vision Transformers Learn?

arXiv 2023

2023

Language-only Efficient Training of Zero-shot Composed Image Retrieval

arXiv 2023

2023

Prometheus: Inducing Fine-grained Evaluation Capability in Language Models

arXiv 2023

2023

Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models

arXiv 2023

2023

Masking meets Supervision: A Strong Learning Alliance

CVPR 2025 1

2023

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

neural-relation-graph-a-unified-framework-for

2023

Compressed Context Memory For Online Language Model Interaction

arXiv 2023

2023

Who Wrote this Code? Watermarking for Code Generation

arXiv 2023

2023

Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts

arXiv 2023

2023

MPCHAT: Towards Multimodal Persona-Grounded Conversation

arXiv 2023

2023

Towards Calibrated Robust Fine-Tuning of Vision-Language Models

arXiv 2023

2023

Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images

arXiv 2023

2023

Dataset Condensation via Efficient Synthetic-Data Parameterization

arXiv 2022

2022

Dataset Condensation with Contrastive Signals

arXiv 2022

2022

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

CVPR 2022 1

2022

OCR-free Document Understanding Transformer

arXiv 2021

2021

Rethinking Spatial Dimensions of Vision Transformers

ICCV 2021 10

2021

Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels

CVPR 2021 1

2021

Rethinking Channel Dimensions for Efficient Model Design

CVPR 2021 1

2020

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights

adamp-slowing-down-the-slowdown-for-momentum

2020

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

what-is-wrong-with-scene-text-recognition-1

2019

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

cutmix-regularization-strategy-to-train-1

2019

Learning De-biased Representations with Biased Representations

ICML 2020 1

2019

EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

arXiv 2019

2019

Affiliations

No known affiliations.

Frequent co-authors

10

from 43 papers