4 papers
Compression Asymmetry and Trajectory Binding in Noise-Anchored Diffusion Inversion
Yongseong Park, Joeun Kim, HoEun Kim +1
Real-image diffusion inversion is governed by a tight quality-cost trade-off, with costs incurred in computation, storage, or per-image optimization. We study this trade-off throug…
CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking
Joeun Kim, HoEun Kim, Young-Sik Kim
Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining strict false-positive control. Existing ECC-based LLM watermark…
Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
Joeun Kim, HoEun Kim, Dongsup Jin +1
Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that exi…
References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation
Doyoung Kim, Youngjun Lee, Joeun Kim +4
Conversational query reformulation (CQR) has become indispensable for improving retrieval in dialogue-based applications. However, existing approaches typically rely on reference p…