Publications

2026

ECCV 2026

JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation

# 3D Generation # Vision # HOI

Mingyeong Song, Jungbin Cho, Jisoo Kim, Ananya Bal, Kartik Sharma, Youngjae Yu, Laszlo A. Jeni, Junhyug Noh

ECCV 2026

Spanning Tree Autoregressive Visual Generation

# Image Generation # Autoregressive # Vision

Sangkyu Lee, Changho Lee, Janghoon Han, Hosung Song, Tackgeun You, Hwasup Lim, Stanley Jungkyu Choi, Honglak Lee, Youngjae Yu

Arxiv

Real-Time Execution with Autoregressive Policies

# VLA # Real-Time Execution # Robot Learning

Sangkyu Lee, Seohyeon Park, Tackgeun You, Avi Caciularu, Idan Szpektor, Hwasup Lim, Youngjae Yu

Arxiv

ResearchMath-14K: Scaling Research-Level Mathematics via Agents

# Math # Reasoning # Agentic AI

Guijin Son, Seungyeop Yi, Minju Gwak, Hyunwoo Ko, Wongi Jang, Youngjae Yu

Arxiv

Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback

# LLM Agents # CAD Generation # FEA

Guijin Son*, Jehyun Park*, Seyeon Park, Sunghee Ahn, Youngjae Yu

Arxiv

ICRA 2026 Workshop

vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models

# Vision-Language-Action # Evaluation Harness # Robotic

Suhwan Choi, Yunsung Lee, Yubeen Park, Chris Dongjoo Kim, Ranjay Krishna, Dieter Fox, Youngjae Yu

Arxiv

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

# LLM # Math Reasoning # Benchmark

Guijin Son, et al.

Arxiv

ICLR 2026 Workshop

Random Is Hard to Beat: Active Selection in Online DPO with Modern LLMs

# LLM # DPO # Alignment

Giyeong Oh, Junghyun Lee, Jaehyun Park, Youngjae Yu, Wonho Bae, Junhyug Noh

Arxiv

CVPR 2026 Workshop

CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents

# Robotics # Navigation # Evaluation

Haebin Seong*, Sungmin Kim*, Yongjun Cho*, et al. (Corresponding authors: Youngjae Yu, Yunsung Lee)

Arxiv

ICML 2026 (Spotlight)

Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math

# LLM # Reasoning # Benchmark

Guijin Son, Donghun Yang, Hitesh Laxmichand Patel, Hyunwoo Ko, Amit Agarwal, Sunghee Ahn, Kyong-Ha Lee, Youngjae Yu

Arxiv

UR 2026

XNav-Pipe: Cross-Platform Robot Navigation Data Generation Pipeline

# Robotics # Data Generation # Simulation

Sungwoong Kim, Minseo Kim, Siyeol Kim, Junhee Park, Youngjae Yu

ACL 2026

Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification

# NLP # Text Simplification # Multilingual

Jinhong Jeong, Junghun Park, Youngjae Yu

Arxiv

ACL 2026

GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance

# Multimodal # Video # Egocentric

Junhyeok Kim*, Jaewoo Park*, Junhee Park, Sangeyl Lee, Jiwan Chung, Jisung Kim, Ji Hoon Joung, Youngjae Yu

Arxiv

ACL 2026

Mind the Motions: Benchmarking Theory‑of‑Mind in Everyday Body Language

# Theory of Mind # Video # Nonverbal

Seungbeen Lee, Jinhong Jeong, Donghyun Kim, Yejin Son, Youngjae Yu

Arxiv

ACL 2026

Investigating Counterfactual Unfairness in LLMs towards Identities through Humor

# LLM # Fairness # Humor

Shubin Kim*, Yejin Son*, Junyeong Park, Keummin Ka, Seungbeen Lee, Jaeyoung Lee, Hyeju Jang, Alice Oh, Youngjae Yu

Arxiv

ACL 2026

Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding

# MLLM # Benchmark # UI/UX

Jaehyun Jeon, Min Soo Kim, Janghan Yoon, Sumin Shim, Yejin Choi, Hanbin Kim, Dae Hyun Kim, Youngjae Yu

Arxiv

ACL 2026 Findings

Tracing Mathematical Proficiency Through Problem-Solving Processes

# LLM # Knowledge Tracing # Education

Jungyang Park*, Suho Kang*, Jaewoo Park, Jae Hong Kim, Jaewoo Shin, Seonjoon Park, Youngjae Yu

Arxiv

ACL 2026 Findings

DUSK: Do Not Unlearn Shared Knowledge

# LLM # Unlearning # Privacy

Wonje Jeung*, Sangyeon Yoon*, Hyesoo Hong, Soeun Kim, Seungju Han, Youngjae Yu, Albert No

Arxiv

ACL 2026 Findings

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

# VLM # Benchmark # Multimodal

Dasol Choi*, Guijin Son*, Hanwool Lee*, Minhyuk Kim, Hyunwoo Ko, TEABIN LIM, Eungyeol Ahn, Jungwhan Kim, Seunghyeok Hong, Youngsook Song

Arxiv

ACL 2026 Findings

Revisiting the Uniform Information Density Hypothesis in LLM Reasoning

# LLM # Reasoning # CoT

Minju Gwak, Guijin Son, Jaehyung Kim

Arxiv

LREC 2026

Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models

# LLM Evaluation # NLP # Benchmark

Hanwool Lee*, Dasol Choi*, Sooyong Kim, Ilgyun Jeong, Sangwon Baek, Guijin Son, Inseon Hwang, Naeun Lee, Seunghyeok Hong

Arxiv

ICLR 2026

TIPO: Text to Image with Text Presampling for Prompt Optimization

# Image Generation # Diffusion # Prompt Optimization

Shih-Ying Yeh*, Sang-Hyun Park*, Giyeong Oh, Min Song, Youngjae Yu

Arxiv

ICLR 2026

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

# EmbodiedAI # Multimodal # Video

Suwhan Choi*, Jaeyoon Jung*, Haebin Seong*, Minchan Kim, Minyeong Kim, Yongjun Cho, Yoonshik Kim, Yubeen Park, Youngjae Yu, Yunsung Lee

Arxiv

ICLR 2026

Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought

# NLP # Multilingual # CoT

Guijin Son, Donghun Yang, Hitesh Laxmichand Patel, Amit Agarwal, Hyunwoo Ko, Chanuk lim, Srikant Panda, Minhyuk Kim, Nikunj drolia, Dasol Choi, Kyong-Ha Lee, Youngjae Yu

Arxiv

ICLR 2026

Teaching Metric Distance to Autoregressive Multimodal Foundational Models

# Multimodal # MLLM

Jiwan Chung, Saejin Kim, Yongrae Jo, Jaewoo Park, Dongjun Min, Youngjae Yu

Arxiv

AAAI 2026 (Oral)

Do Language Models Associate Sound with Meaning? A Multimodal Study of Sound Symbolism

# Multimodal # AudioLLM

Jinhong Jeong*, Sunghyun Lee*, Jaeyoung Lee, Seonah Han, Youngjae Yu

Arxiv

AAAI 2026

Explain with Visual Keypoints Like a Real Mentor! A Benchmark for Multimodal Solution Explanation

# Multimodal # LLM # Benchmark

Jaewoo Park*, Jungyang Park*, Dongju Jang, Jiwan Chung, Byungwoo Yoo, Jaewoo Shin, Seonjoon Park, Taehyeong Kim, Youngjae Yu

Arxiv

2025

A11YN: aligning LLMs for accessible web UI code generation

# LLM # WebUI # Accessibility

Janghan Yoon, Jaegwan Cho, Junhyeok Kim, Jiwan Chung, Jaehyun Jeon, Youngjae Yu

Arxiv

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

# Diffusion # 3D Generation # Scene-aware

Jungbin Cho, Minsu Kim, Jisoo Kim, Ce Zheng, Laszlo A. Jeni, Ming-Hsuan Yang, Youngjae Yu, Seonjoo Kim

Arxiv

What MLLMs Learn about When they Learn about Multimodal Reasoning

# Multimodal Reasoning # Multimodal # Benchmark

Jiwan Chung, Neel Joshi, Pratyusha Sharma, Youngjae Yu, Vibhav Vineet

Arxiv

InfoCausalQA:Can Models Perform Non-explicit Causal Reasoning Based on Infographic?

# Causal QA # Benchmark # VLM

Keummin Ka, Junhyeong Park, Jaehyun Jeon, Youngjae Yu

Arxiv

Humanoids 2025 (Workshop)

Baymax in Reality: A Humanoid System for Non-Contact Health Monitoring and Empathetic Interaction

# Robotics # Humanoid

Junhyeong Park, Taemoon Jeong, Minseo Kwak, Jisoo Kim, Seungbeen Lee, Sungjoon Choi, Youngjae Yu

Humanoids 2025 (Workshop)

K-pop Demon Robots

# Robotics # Humanoid

Sungwoong Kim, Minseo Kim, Siyeol Kim, Hwasup Lim, Youngjae Yu

CIKM 2025

NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance

# Cross-lingual # Embeddings

Hanwool Lee*, Sara Yu*, Yewon Hwang*, Jonghyun Choi, Heejae Ahn, Sungbum Jung, Youngjae Yu

Arxiv

NeurIPS 2025

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks

# Computer Vision

Giyeong Oh, Woohyun Cho, Siyeol Kim, Suhwan Choi, Youngjae Yu

Arxiv

NeurIPS 2025

KL Penalty Control via Perturbation for Direct Preference Optimization

# LLM # DPO # Human Preference

Sangkyu Lee, Janghoon Han, Hosung Song, Stanley Jungkyu Choi, Honglak Lee, Youngjae Yu

Arxiv

NeurIPS 2025

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation

# Computer Vision

Jeongin Kim, Wonho Bae, YouLee Han, Giyeong Oh, Youngjae Yu, Danica J. Sutherland, Junhyug Noh

Arxiv

EMNLP 2025

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making

# Embodied AI # LLM # Safety

Yejin Son*, Minseo Kim*, Sungwoong Kim, Seungju Han, Jian Kim, Dongju Jang, Youngjae Yu, Chanyoung Park

Arxiv

EMNLP 2025

VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms

# Multimodal # Agent # Reasoning

Seungwon Lim, Sungwoong Kim, Jihwan Yu, Sungjae Lee, Jiwan Chung, Youngjae Yu

Arxiv

EMNLP 2025

Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation

# Multimodal # Document # Information Retrieval

Yejin Choi*, Jaewoo Park*, Janghan Yoon, Saejin Kim, Jaehyun Jeon, Youngjae Yu

Arxiv

EMNLP 2025

MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation

# Multimodal # Audio # Video

Woohyun Cho, Youngmin Kim, Sunghyun Lee, Youngjae Yu

Arxiv

EMNLP 2025 (Findings)

Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd

# Multimodal # Commonsense Reasoning # Abductive Reasoning

Yejin Son*, Saejin Kim*, Dongjun Min, Youngjae Yu

Arxiv

COLM 2025

G1yphD3c0de: Towards Safer Language Models on Visually Perturbed Texts

# Multimodal # Safety # Societal Implications

Yejin Choi, Yejin Yeo, Yejin Son, Seungju Han, Youngjae Yu

COLM 2025

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

# NLP # Fact Verification

Wooseok Seo*, Seungju Han*, Jaehun Jung, Benjamin Newman, Seungwon Lim, Seungbeen Lee, Ximing Lu, Yejin Choi, Youngjae Yu

Arxiv

COLM 2025

HIPPO-VIDEO : Simulating Watch Histories with Large Language Models for History-Driven Video Highlighting

# Multimodal # Video

Jeongeun Lee, Youngjae Yu, Dongha Lee

Arxiv

ICCV 2025

V.I.P.: Iterative Online Preference Distillation for Efficient Video Diffusion Models

# Video Generation # Distillation # Preference Learning

Jisoo Kim, Wooseok Seo, Junwan Kim, Seungho Park, Sooyeon Park, Youngjae Yu

Arxiv

ICCV 2025

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

# 3D # Human Motion # Generation

Jungbin Cho*, Junwan Kim*, Jisoo Kim, Minseo Kim, Mingu Kang, Sungeun Hong, Tae-Hyun Oh, Youngjae Yu

Arxiv

ICCV 2025

VAGUE: Visual Contexts Clarify Ambiguous Expressions

# Multimodal # Ambiguity

Heejeong Nam, Jinwoo Ahn, Keummin Ka, Jiwan Chung, Youngjae Yu

Arxiv

MICCAI 2025

Scalp Diagnostic System With Label-Free Segmentation and Training-Free Image Translation

# Computer Vision # Scalp Diagnosis # Image Translation

Youngmin Kim*, Saejin Kim*, Hoyeon Moon, Youngjae Yu, Junhyug Noh

Arxiv

ACL 2025

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues

# Multimodal # Nonverbal Conversation # Video # 3D

Youngmin Kim*, Jiwan Chung*, Jisoo Kim, Sunghyun Lee, Sangkyu Lee, Junhyeok Kim, Cheoljong Yang, Youngjae Yu

Arxiv

ACL 2025 (Oral)

Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games

# NLP # Personality # Reinforcement Learning

Seungwon Lim, Seungbeen Lee, Dongjun Min, Youngjae Yu

Arxiv

ACL 2025

Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?

# Multimodal # MLLM

Jiwan Chung, Janghan Yoon, Junhyeong Park, Sangeyl Lee, Joowon Yang, Sooyeon Park, Youngjae Yu

Arxiv

ACL 2025

Representation Bending for Large Language Model Safety

# NLP # LLM # Safety

Ashkan Yousefpour*, Taeheon Kim*, Ryan S. Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Harrison Ngan, Youngjae Yu, Jonghyun Choi

Arxiv

SlumpGuard: An AI-Powered Real-Time System for Automated Concrete Slump Prediction via Video Analysis

# Computer Vision # Video # Industrial Application

Youngmin Kim*, Giyeong Oh*, Kwangsoo Youm, Youngjae Yu

Arxiv

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

# Multimodal # Reasoning

Jiwan Chung*, Junhyeok Kim*, Siyeol Kim, Jaeyoung Lee, Minsoo Kim, Youngjae Yu

Arxiv

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

# multimodal # MLLM # AI for Science

Guijin Son, Jiwoo Hong, Honglu Fan, Heejeong Nam, Hyunwoo Ko, Seungwon Lim, Jinyeop Song, Jinha Choi, Gonçalo Paulo, Youngjae Yu

Arxiv

Explain with Visual Keypoints Like a Real Mentor! A Benchmark for Multimodal Solution Explanation

# NLP # Math # Education

Jaewoo Park*, Jungyang Park*, Dongju Jang, Jiwan Chung, Byungwoo Yoo, Jaewoo Shin, Seonjoon Park, Taehyeong Kim, Youngjae Yu

Arxiv

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

# LLM # Watermark # Low-rank Adaptation

Giyeong Oh, Saejin Kim, Woohyun Cho, Sangkyu Lee, Jiwan Chung, Dokyung Song, Youngjae Yu

Arxiv

ICRA 2025

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

# Embodied AI # Robotics # Navigation

Suhwan Choi, Yongjun Cho, Minchan Kim, Jaeyoon Jung, Myunchul Joe, Yubeen Park, Minseo Kim, Sungwoong Kim, Sungjae Lee, Hwiseong Park, Jiwan Chung, Youngjae Yu

Arxiv

NAACL 2025 (Oral)

C^2 : Scalable Auto-Feedback for LLM-based Chart Generation

# Multimodal # LLM # Chart Generation

Woosung Koh*, Janghan Yoon*, Minhyung Lee, Youngjin Song, Jaegwan Cho, Jaehyun Kang, Taehyeon Kim, Seyoung Yun, Youngjae Yu, Bongshin Lee

Arxiv

NAACL 2025 (Findings)

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics

# NLP # Personality # Psychometrics

Seungbeen Lee*, Seungwon Lim*, Seungju Han, Giyeong Oh, Jiwan Chung, Minju Kim, Yeonsoo Lee, Dongha Lee, Jinyoung Yeo, Youngjae Yu

Arxiv

NAACL 2025 (Findings)

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

# Multimodal # Egocentric # Dialogue System

Junhyeok Kim, Minsoo Kim, Jiwan Chung, Jungbin Cho, Jisoo Kim, Sungwoong Kim, Gyeongbo Sim, Youngjae Yu

Arxiv

AAAI 2025

DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation

# 3D # Speech # Facial expression

Jisoo Kim*, Jungbin Cho*, Joonho Park, Soonmin Hwang, Da Eun Kim, Geon Kim, Youngjae Yu

Arxiv

AAAI 2025

MASS: Overcoming Language Bias in Image-Text Matching

# Multimodal # Debiasing

Jiwan Chung, Seungwon Lim, Sangkyu Lee, Youngjae Yu

Arxiv

AAAI 2025

i-SRT: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective Judgment

# Multimodal # Video LLM # Preference

Daechul Ahn, Yura Choi, San Kim, Youngjae Yu, Dongyeop Kang, Jonghyun Choi

Arxiv