5 papers
Grounded Revision vs. Prior Injection: Probing Retrieval-Augmented Patent Claim Amendment
Josepha Michiko Leo, Hyun-seok Min, Yehoon Jang +3
Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely tested where "correct" has a def…
PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks
Yehoon Jang, Chaewon Lee, Hyun-seok Min +1
The Patent Trial and Appeal Board (PTAB) of the USPTO adjudicates thousands of ex parte appeals each year, requiring the integration of technical understanding and legal reasoning.…
Soft Filtering: Guiding Zero-shot Composed Image Retrieval with Prescriptive and Proscriptive Constraints
Youjin Jung, Seongwoo Cho, Hyun-seok Min +1
Composed Image Retrieval (CIR) aims to find a target image that aligns with user intent, expressed through a reference image and a modification text. While Zero-shot CIR (ZS-CIR) m…
STELLAR: Scene Text Editor for Low-Resource Languages and Real-World Data
Yongdeuk Seo, Hyun-seok Min, Sungchul Choi
Scene Text Editing (STE) is the task of modifying text content in an image while preserving its visual style, such as font, color, and background. While recent diffusion-based appr…
DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling
Kyuheon Jung, Yongdeuk Seo, Seongwoo Cho +3
In this paper, we present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) to tackle the challenges inherent in data-scar…