10 citations · 17 across the 23 of their papers we have counts for
23 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)…
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…
Temporal Information Retrieval via Time-Specifier Model Merging
SeungYoon Han, Taeho Hwang, Sukmin Cho +4
The rapid expansion of digital information and knowledge across structured and unstructured sources has heightened the importance of Information Retrieval (IR). While dense retriev…
Does Rationale Quality Matter? Enhancing Mental Disorder Detection via Selective Reasoning Distillation
Hoyun Song, Huije Lee, Jisu Shin +3
The detection of mental health problems from social media and the interpretation of these results have been extensively explored. Research has shown that incorporating clinical sym…
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Sukmin Cho, Sangjin Choi, Taeho Hwang +6
Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding,…
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…
PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling
Junmyeong Lee, Eui Jun Hwang, Sukmin Cho +1
In Masked Image Modeling (MIM), two primary methods exist: Pixel MIM and Latent MIM, each utilizing different reconstruction targets, raw pixels and latent representations, respect…
EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
Taeho Hwang, Sukmin Cho, Soyeong Jeong +3
We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA…
Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling
Huije Lee, Hoyun Song, Jisu Shin +3
Trolling in online communities typically involves disruptive behaviors such as provoking anger and manipulating discussions, leading to a polarized atmosphere and emotional distres…
An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs
Eui Jun Hwang, Sukmin Cho, Junmyeong Lee +1
Gloss-free Sign Language Translation (SLT) converts sign videos directly into spoken language sentences without relying on glosses. Recently, Large Language Models (LLMs) have show…
DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation
Taeho Hwang, Soyeong Jeong, Sukmin Cho +2
Recent advancements in Large Language Models (LLMs) have significantly improved their performance across various Natural Language Processing (NLP) tasks. However, LLMs still strugg…
A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production
Eui Jun Hwang, Sukmin Cho, Huije Lee +2
This work addresses the challenges associated with the use of glosses in both Sign Language Translation (SLT) and Sign Language Production (SLP). While glosses have long been used…
Self-Knowledge Distillation for Learning Ambiguity
Hancheol Park, Soyeong Jeong, Sukmin Cho +1
Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that c…
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…
Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations
Sukmin Cho, Soyeong Jeong, Jeongyeon Seo +2
The robustness of recent Large Language Models (LLMs) has become increasingly crucial as their applicability expands across various domains and real-world applications. Retrieval-A…
Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
Soyeong Jeong, Jinheon Baek, Sukmin Cho +2
Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to en…
Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering
Sukmin Cho, Jeongyeon Seo, Soyeong Jeong +1
Large language models (LLMs) enable zero-shot approaches in open-domain question answering (ODQA), yet with limited advancements as the reader is compared to the retriever. This st…
Test-Time Self-Adaptive Small Language Models for Question Answering
Soyeong Jeong, Jinheon Baek, Sukmin Cho +2
Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to mem…
Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker
Sukmin Cho, Soyeong Jeong, Jeongyeon Seo +1
Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-…
Non-Autoregressive Sign Language Production via Knowledge Distillation
Eui Jun Hwang, Jung Ho Kim, Suk Min Cho +1
Sign Language Production (SLP) aims to translate expressions in spoken language into corresponding ones in sign language, such as skeleton-based sign poses or videos. Existing SLP…
Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation
Soyeong Jeong, Jinheon Baek, Sukmin Cho +2
Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkab…