7 papers
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…
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…
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…
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…
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…
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language Models
Jongwook Han, Jongwon Lim, Injin Kong +1
Large language models can express values in two main ways: (1) intrinsic expression, reflecting the model's inherent values learned during training, and (2) prompted expression, el…
Style Extraction on Text Embeddings Using VAE and Parallel Dataset
InJin Kong, Shinyee Kang, Yuna Park +2
This study investigates the stylistic differences among various Bible translations using a Variational Autoencoder (VAE) model. By embedding textual data into high-dimensional vect…