PUBLICATIONS

2026

Real-Time Execution with Autoregressive Policies
CoRL 2026
# VLA # Real-Time Execution # Robot Learning

Real-Time Execution with Autoregressive Policies

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

arXiv

CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents
CoRL 2026
# Robotics # Navigation # Evaluation

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

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

arXiv

PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control
# Robotics # Multimodal # VLA

PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control

Suhwan Choi, Jaeyoon Jung, Sungkyung Kim, Yunsung Lee, Youngjae Yu

arXiv

Small Models Scout Bottleneck Order for Large-Model Data Control
# LLM # Data Curation # Efficient AI

Small Models Scout Bottleneck Order for Large-Model Data Control

Seungmin Choi, Jiwon Sung, Muhammad Umer, Abhiram Rao Gorle, Guijin Son, Youngjae Yu, John M. Cioffi

arXiv

Negation Without Confusion: Decomposing Bias and Recomposing Style in Text Embeddings for Negation-Aware Image Generation
EMNLP 2026
# Image Generation # Multimodal

Negation Without Confusion: Decomposing Bias and Recomposing Style in Text Embeddings for Negation-Aware Image Generation

Sooyeon Park, Hemraj Singh, Kyunghyun Min, Youngjae Yu, Sung-Bae Cho

Same Trajectory, Contradictory Rewards (RoboRMBench): Paraphrase Fragility in Vision Language Reward Models
EMNLP 2026
# Vlm # Robotics # Benchmark

Same Trajectory, Contradictory Rewards (RoboRMBench): Paraphrase Fragility in Vision Language Reward Models

Wonje Jeung, Sangyeon Yoon, Hyesoo Hong, Yoonjun Cho, Dongjae Jeon, Bumjun Kim, Jean Oh, Youngjae Yu, Albert No

arXiv

Anchored by an Afterthought: Cross-Modal Numerical Anchoring in VLMs
EMNLP 2026 Findings
# Vlm # Multimodal # Reasoning

Anchored by an Afterthought: Cross-Modal Numerical Anchoring in VLMs

Taehyeon Park, Jeonghun Park, Youngjae Yu

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents
EMNLP 2026 Findings
# Robotics # Embodied AI # AI Safety

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents

Hyunse Lee, Jiwoo Jeong, Haneul Lee, Kyochul Jang, Youngjae Yu, Woojin Lee

arXiv

Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language
EMNLP 2026 Findings
# VLM # Multimodal # Benchmark

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

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

arXiv

ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languages
# NLP # Multilingual # Conlang

ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languages

Jinhong Jeong, Seungyeop Yi, Sangah Lee, Youngjae Yu

arXiv

The Wedge Questions: Latent Cultural Boundaries in LLMs via Persona Projection Divergence
ICML 2026 Workshop
# NLP # LLM Alignment # Human-Centered AI

The Wedge Questions: Latent Cultural Boundaries in LLMs via Persona Projection Divergence

Yejin Son, Yongjin Yang, Ryan Faulkner, Matt Ratto, Seungwon Lim, Youngjae Yu, Zhijing Jin

A11YN: aligning LLMs for accessible web UI code generation
COLM 2026
# LLM # WebUI # Accessibility

A11YN: aligning LLMs for accessible web UI code generation

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

arXiv

v1: Learning to Point Visual Tokens for Multimodal Mathematical Grounded Reasoning
COLM 2026
# Multimodal # Visual Grounding # NLP

v1: Learning to Point Visual Tokens for Multimodal Mathematical Grounded Reasoning

Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee, Min Soo Kim, Youngjae Yu

arXiv

MicroVLA: Edge-Deployable Vision Language Action at 10M Parameters
RSS 2026 Workshop
# VLA # Robotics

MicroVLA: Edge-Deployable Vision Language Action at 10M Parameters

Ngseo Kim, Junghyun Kim, Gi-Cheon Kang, Youngjae Yu, Byoung-Tak Zhang

JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation
ECCV 2026
# 3D Generation # Vision # HOI

JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation

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

arXiv

Spanning Tree Autoregressive Visual Generation
ECCV 2026
# Image Generation # Autoregressive # Vision

Spanning Tree Autoregressive Visual Generation

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

arXiv

ResearchMath-14K: Scaling Research-Level Mathematics via Agents
# Math # Reasoning # Agentic AI

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

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

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

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

arXiv

vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models
ICRA 2026 Workshop
# Vision-Language-Action # Evaluation Harness # Robotic

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

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

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

Guijin Son, et al.

arXiv

Random Is Hard to Beat: Active Selection in Online DPO with Modern LLMs
ICLR 2026 Workshop
# LLM # DPO # Alignment

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

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

arXiv

Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math
ICML 2026 (Spotlight)
# LLM # Reasoning # Benchmark

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

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

arXiv

XNav-Pipe: Cross-Platform Robot Navigation Data Generation Pipeline
UR 2026
# Robotics # Data Generation # Simulation

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

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

Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification
ACL 2026
# NLP # Text Simplification # Multilingual

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

Jinhong Jeong, Junghun Park, Youngjae Yu

arXiv

GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance
ACL 2026
# Multimodal # Video # Egocentric

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

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

arXiv

Investigating Counterfactual Unfairness in LLMs towards Identities through Humor
ACL 2026
# LLM # Fairness # Humor

Investigating Counterfactual Unfairness in LLMs towards Identities through Humor

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

arXiv

Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding
ACL 2026
# MLLM # Benchmark # UI/UX

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

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

arXiv

Tracing Mathematical Proficiency Through Problem-Solving Processes
ACL 2026 Findings
# LLM # Knowledge Tracing # Education

Tracing Mathematical Proficiency Through Problem-Solving Processes

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

arXiv

DUSK: Do Not Unlearn Shared Knowledge
ACL 2026 Findings
# LLM # Unlearning # Privacy

DUSK: Do Not Unlearn Shared Knowledge

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

arXiv

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models
ACL 2026 Findings
# VLM # Benchmark # Multimodal

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

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

arXiv

Revisiting the Uniform Information Density Hypothesis in LLM Reasoning
ACL 2026 Findings
# LLM # Reasoning # CoT

Revisiting the Uniform Information Density Hypothesis in LLM Reasoning

Minju Gwak, Guijin Son, Jaehyung Kim

arXiv

Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models
LREC 2026
# LLM Evaluation # NLP # Benchmark

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

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

arXiv

TIPO: Text to Image with Text Presampling for Prompt Optimization
ICLR 2026
# Image Generation # Diffusion # Prompt Optimization

TIPO: Text to Image with Text Presampling for Prompt Optimization

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

arXiv

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
ICLR 2026
# EmbodiedAI # Multimodal # Video

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

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

arXiv

Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought
ICLR 2026
# NLP # Multilingual # CoT

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

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

Teaching Metric Distance to Autoregressive Multimodal Foundational Models
ICLR 2026
# Multimodal # MLLM

Teaching Metric Distance to Autoregressive Multimodal Foundational Models

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

arXiv

Do Language Models Associate Sound with Meaning? A Multimodal Study of Sound Symbolism
AAAI 2026 (Oral)
# Multimodal # AudioLLM

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

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

arXiv

Explain with Visual Keypoints Like a Real Mentor! A Benchmark for Multimodal Solution Explanation
AAAI 2026
# Multimodal # LLM # Benchmark

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

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

arXiv

2025

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion
# Diffusion # 3D Generation # Scene-aware

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

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

What MLLMs Learn about When they Learn about Multimodal Reasoning

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

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

Keummin Ka, Junhyeong Park, Jaehyun Jeon, Youngjae Yu

arXiv

Baymax in Reality: A Humanoid System for Non-Contact Health Monitoring and Empathetic Interaction
Humanoids 2025 (Workshop)
# Robotics # Humanoid

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

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

K-pop Demon Robots
Humanoids 2025 (Workshop)
# Robotics # Humanoid

K-pop Demon Robots

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

NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance
CIKM 2025
# Cross-lingual # Embeddings

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

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

arXiv

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
NeurIPS 2025
# Computer Vision

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

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

arXiv

KL Penalty Control via Perturbation for Direct Preference Optimization
NeurIPS 2025
# LLM # DPO # Human Preference

KL Penalty Control via Perturbation for Direct Preference Optimization

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

arXiv

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
NeurIPS 2025
# Computer Vision

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

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

arXiv

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making
EMNLP 2025
# Embodied AI # LLM # Safety

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

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

arXiv

VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms
EMNLP 2025
# Multimodal # Agent # Reasoning

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

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

arXiv

Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
EMNLP 2025
# Multimodal # Document # Information Retrieval

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

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

arXiv

MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation
EMNLP 2025
# Multimodal # Audio # Video

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

Woohyun Cho, Youngmin Kim, Sunghyun Lee, Youngjae Yu

arXiv

Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd
EMNLP 2025 (Findings)
# Multimodal # Commonsense Reasoning # Abductive Reasoning

Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd

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

arXiv

G1yphD3c0de: Towards Safer Language Models on Visually Perturbed Texts
COLM 2025
# Multimodal # Safety # Societal Implications

G1yphD3c0de: Towards Safer Language Models on Visually Perturbed Texts

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

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
COLM 2025
# NLP # Fact Verification

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

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

arXiv

HIPPO-VIDEO : Simulating Watch Histories with Large Language Models for History-Driven Video Highlighting
COLM 2025
# Multimodal # Video

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

Jeongeun Lee, Youngjae Yu, Dongha Lee

arXiv

V.I.P.: Iterative Online Preference Distillation for Efficient Video Diffusion Models
ICCV 2025
# Video Generation # Distillation # Preference Learning

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

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

arXiv

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
ICCV 2025
# 3D # Human Motion # Generation

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

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

arXiv

VAGUE: Visual Contexts Clarify Ambiguous Expressions
ICCV 2025
# Multimodal # Ambiguity

VAGUE: Visual Contexts Clarify Ambiguous Expressions

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

arXiv

Scalp Diagnostic System With Label-Free Segmentation and Training-Free Image Translation
MICCAI 2025
# Computer Vision # Scalp Diagnosis # Image Translation

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

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

arXiv

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
ACL 2025
# Multimodal # Nonverbal Conversation # Video # 3D

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

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

arXiv

Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games
ACL 2025 (Oral)
# NLP # Personality # Reinforcement Learning

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

Seungwon Lim, Seungbeen Lee, Dongjun Min, Youngjae Yu

arXiv

Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?
ACL 2025
# Multimodal # MLLM

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

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

arXiv

Representation Bending for Large Language Model Safety
ACL 2025
# NLP # LLM # Safety

Representation Bending for Large Language Model 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

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

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

arXiv

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

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

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

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

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

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

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

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

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

arXiv

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
ICRA 2025
# Embodied AI # Robotics # Navigation

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

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

C^2 : Scalable Auto-Feedback for LLM-based Chart Generation
NAACL 2025 (Oral)
# Multimodal # LLM # Chart Generation

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

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

arXiv

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics
NAACL 2025 (Findings)
# NLP # Personality # Psychometrics

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

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

arXiv

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
NAACL 2025 (Findings)
# Multimodal # Egocentric # Dialogue System

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

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

arXiv

DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation
AAAI 2025
# 3D # Speech # Facial expression

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

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

arXiv

MASS: Overcoming Language Bias in Image-Text Matching
AAAI 2025
# Multimodal # Debiasing

MASS: Overcoming Language Bias in Image-Text Matching

Jiwan Chung, Seungwon Lim, Sangkyu Lee, Youngjae Yu

arXiv

i-SRT: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective Judgment
AAAI 2025
# Multimodal # Video LLM # Preference

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

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

arXiv