Author

Yohan Jo

Observed name: Jo, Yohan

Institution: Seoul National University

Observed institution: Seoul National University

OpenAlex ID: A5094123497

Towards Lifelong Dialogue Agents via Timeline-based Memory Management

2025 · Kai Tzu-iunn Ong, Namyoung Kim, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 7

How Do LLMs Change Predictions Under Negation?

2026 · Yoon, Jongwook, Lim, Jongwon, et al. · arXiv (Cornell University)

Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It

2026 · Song, Jonghyun, Park, Haewon, et al. · arXiv (Cornell University)

Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults

2026 · Suh, Heejae, Han, Jongwook, et al. · arXiv (Cornell University)

The Low-Rank Structure of VLA Reinforcement Learning

2026 · Oh, Minjae, Park, Yoonah, et al. · arXiv (Cornell University)

Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models

2026 · Kong, Injin, Choi, Sunghwan, et al. · arXiv (Cornell University)

AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks

2026 · Song, Woojung, Yang, Hoyeol, et al. · arXiv (Cornell University)

Agents' Overreliance on Unreliable Tools

2026 · Yang, Hoyeol, Song, Woojung, et al. · arXiv (Cornell University)

Fine-Grained Multi Image Object Hallucination Benchmark

2026 · Min, Joonki, Kim, Chaeyun, et al. · arXiv (Cornell University)

SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?

2026 · Association for Computational Linguistics 2026, Jo, Yohan, et al. · Underline Science Inc.

Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators

2026 · Association for Computational Linguistics 2026, Jo, Yohan, et al. · Underline Science Inc.

In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents

2026 · Association for Computational Linguistics 2026, Jo, Yohan, et al. · Underline Science Inc.

Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models

2026 · Association for Computational Linguistics 2026, Han, Jongwook, et al. · Underline Science Inc.

Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction

2026 · Association for Computational Linguistics 2026, Jo, Yohan, et al. · Underline Science Inc.

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

2026 · Association for Computational Linguistics 2026, Jo, Yohan, et al. · Underline Science Inc.

Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers

2026 · Association for Computational Linguistics 2026, Heo, Chaewon, et al. · Underline Science Inc.

RobotValues: Evaluating Household Robots When Human Values Conflict

2026 · Han, Jongwook, Kim, Hyeongjin, et al. · arXiv (Cornell University)

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement

2026 · Kong, Injin, Lee, Hyoungjoon, et al. · arXiv (Cornell University)

Can MLLMs Reason About Visual Persuasion? Evaluating the Efficacy and Faithfulness of Reasoning

2026 · Lee, Naeun, Kim, Hyunjong, et al. · arXiv (Cornell University)

KL for a KL: On-Policy Distillation with Control Variate Baseline

2026 · Oh, Minjae, Song, Sangjun, et al. · arXiv (Cornell University)

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States

2026 · Choi, Yunho, Lim, Jongwon, et al. · arXiv (Cornell University)

MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes

2026 · Chen, Maximillian, Zhang, Xuanming, et al. · arXiv (Cornell University)

MatKV: Trading Compute for Flash Storage in LLM Inference

2026 · Kun-Woo Shin, Jay H. Park, et al. · IEEE International Conference on Data Engineering (ICDE)

Towards Motion-aware Referring Image Segmentation

2026 · Kim, Chaeyun, Yi, Seunghoon, et al. · arXiv (Cornell University)

Quantifying Data Contamination in Psychometric Evaluations of LLMs

2026 · Association for Computational Linguistics 2026, Han, Jongwook, et al. · Underline Science Inc.

Works count: 41

Citation count: 7

H-index: 1

I10-index: