13 papers
OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching
Can Xiao, Sukmin Cho, Junbong We +7
Large language model (LLM) inference serving is increasingly constrained by memory rather than compute. As long-context and long-form reasoning workloads become more prevalent, the…
Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval
Junmyeong Lee, Chan Hur, ChangSu Choi +5
Sign Language Retrieval (SLRet) enables efficient access to sign language content but remains fragile in fine-grained scenarios where visually similar signs must be distinguished.…
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
Sangjin Choi, Sukmin Cho, Yifan Xiong +3
In prefill-decode (PD) disaggregated LLM serving, each request is assigned to a decode worker after prefill. Existing decode routers balance only load; for mixture-of-experts (MoE)…
The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems
Chanwoo Choi, Jinsoo Kim, Sukmin Cho +2
With the growing adoption of retrieval-augmented generation (RAG) systems, various attack methods have been proposed to degrade their performance. However, most existing approaches…
Database-Augmented Query Representation for Information Retrieval
Soyeong Jeong, Jinheon Baek, Sukmin Cho +2
Information retrieval models that aim to search for documents relevant to a query have shown multiple successes, which have been applied to diverse tasks. Yet, the query from the u…
Upcycling Candidate Tokens of Large Language Models for Query Expansion
Jinseok Kim, Sukmin Cho, Soyeong Jeong +2
Query Expansion (QE) improves retrieval performance by enriching queries with related terms. Recently, Large Language Models (LLMs) have been used for QE, but existing methods face…