3 citations · 8 across the 41 of their papers we have counts for
54 papers
A fixed-time stable limit theorem for non-normalized functionals on irregular time grids
Yi Guo
Let an Itô semimartingale be observed at times satisfying , where is adapted and càdlàg, and and its reciprocal are bounded on compact in…
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It
Jonghyun Song, Haewon Park, Jeonghoon Shim +2
As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (the sites or services they com…
Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults
Heejae Suh, Jongwook Han, Zahra Gholami +1
Unreliable visual inputs can harm task performance and cause potential physical safety risks for vision-language-action (VLA) models. We analyze how and GR00T models act und…
SelfSearch: Reward-Free Search for Self-Improving Agents
Jungwoo Yang, Injin Kong, In Jin Kong +1
Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing approaches use this ability to…
The Low-Rank Structure of VLA Reinforcement Learning
Minjae Oh, Yoonah Park, Jongwon Lim +1
Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, yet how RL reshapes these policies remains poorly understood. We find that RL ac…
Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models
Injin Kong, Sunghwan Choi, Yohan Jo
Masked diffusion language models (MDMs) admit flexible generation orders, making the unmasking strategy an inference decision. Existing methods vary in how they prioritize position…
AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks
Woojung Song, Hoyeol Yang, Jeonghoon Shim +4
Large language model (LLM) agents assist users with everyday tasks that can be completed in many reasonable ways. Even when their answers are useful, how agents carry out these tas…
ProTTT: Learning to Learn Semantic User Memory with Test-Time Training
Sejun Park, Hyoungjo Bhang, Hyein Jeong +1
Personalization requires language models to capture user-specific knowledge from a growing user history. Existing context-based approaches incur increasing inference costs as user…
Agents' Overreliance on Unreliable Tools
Hoyeol Yang, Woojung Song, Taewon Kim +3
LLM agents use tools to access information and perform computations beyond their parametric knowledge. Existing tool-use benchmarks evaluate whether agents select and call the righ…
Fine-Grained Multi Image Object Hallucination Benchmark
Joonki Min, Chaeyun Kim, Hyungwook Choi +4
Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. However, current MLLMs remain fundam…
SHAPE of Thinking: Mathematical Heuristics for Analyzing and Improving LLM Reasoning
Jonghyun Song, Sangjun Song, Minjae Oh +3
Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet final-answer accuracy reveals little about the strategies they use. We introduce \…
RobotValues: Evaluating Household Robots When Human Values Conflict
Jongwook Han, Hyeongjin Kim, Yohan Jo
While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations where robots are expected to choose actions…
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
Woojung Song, Nalim Kim, Sangjun Song +3
Role-playing language agents (RPLAs) simulate specific characters and personas across applications such as entertainment, companionship, interactive storytelling, and education. Fa…
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
Injin Kong, Hyoungjoon Lee, Yohan Jo
Continuous diffusion language models require choosing a representation space in which denoising operates, yet it remains unclear which representations are most compatible with diff…
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
Yunho Choi, Jongwon Lim, Woojin Ahn +3
Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models rests on variance reduction, which requires both a reliable baseline and high prompt diversity with…
Can MLLMs Reason About Visual Persuasion? Evaluating the Efficacy and Faithfulness of Reasoning
Naeun Lee, Hyunjong Kim, Sunghwan Choi +2
Persuasive visuals play a central role in advertising, public communication, and online media, making it increasingly important to understand whether an image is persuasive and why…
KL for a KL: On-Policy Distillation with Control Variate Baseline
Minjae Oh, Sangjun Song, Gyubin Choi +2
On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice…
MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes
Maximillian Chen, Xuanming Zhang, Michael Peng +3
The rise of Internet of Things (IoT) devices in the physical world necessitates voice-based interfaces capable of handling complex user experiences. While modern Large Language Mod…
Towards Motion-aware Referring Image Segmentation
Chaeyun Kim, Seunghoon Yi, Yejin Kim +2
Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-rel…
SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue
Jonggeun Lee, Junseong Pyo, Jeongmin Park +1
Robust voice agents require exposure to the full diversity of how people interact through speech. However, obtaining enough spoken interactions is prohibitively expensive. Building…
Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs
Jeongmoon Won, Seungwon Kook, Yohan Jo
Conversational diagnosis requires multi-turn history-taking, where an agent asks clarifying questions to refine differential diagnoses under incomplete information. Existing approa…
Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
Injin Kong, Hyoungjoon Lee, Yohan Jo
Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) provides an efficient route to diffusion language modeling, but it remains unclear whether…
Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers
Chaewon Heo, Cheyon Jin, Yohan Jo
As emotional support chatbots have recently gained significant traction across both research and industry, a common evaluation strategy has emerged: use help-seeker simulators to i…
Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction
Sejun Park, Yoonah Park, Jongwon Lim +1
Estimating the persuasiveness of messages is critical in various applications, from recommender systems to safety assessment of LLMs. While it is imperative to consider the target…