collaborators

5 papers

cs.CV2026

FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment

Myunsoo Kim, Seongwoong Shim, Byung-Jun Lee

False negatives pose a critical challenge in vision-language pretraining (VLP) due to the many-to-many correspondence between images and texts in large-scale datasets. These false…

cs.LG2026

Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding

Seongwoong Shim, Myunsoo Kim, Jae Hyeon Cho +1

Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window s…

cs.LG2025

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training

Myunsoo Kim, Donghyeon Ki, Seong-Woong Shim +1

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and…

cs.AI2025

Rethinking DPO: The Role of Rejected Responses in Preference Misalignment

Jay Hyeon Cho, JunHyeok Oh, Myunsoo Kim +1

Direct Preference Optimization (DPO) is a simple and efficient framework that has attracted substantial attention. However, it often struggles to meet its primary objectives -- inc…

cs.LG2025

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations

Myunsoo Kim, Hayeong Lee, Seong-Woong Shim +2

Intelligent agents are able to make decisions based on different levels of granularity and duration. Recent advances in skill learning enabled the agent to solve complex, long-hori…