8 papers
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
Gyuwan Kim, Cheoneum Park, Tao Yang
Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, whi…
Global Optimization and Inference-Time Region Grafting for Agentic Workflows
Donghyeok Koh, Gyuwan Kim, Jinyeong Bak +4
Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture selection. However, they determine…
KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
Seongjin Cha, Gyuwan Kim, Dongsu Han +2
Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore th…
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
Byeongjin Kim, Gyuwan Kim, Seo Yeon Park
Large language models (LLMs) struggle with reasoning over long contexts where relevant information is sparsely distributed. Although plan-and-execute frameworks mitigate this by de…
Detecting Training Data of Large Language Models via Expectation Maximization
Gyuwan Kim, Yang Li, Evangelia Spiliopoulou +2
Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as…
AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
Soyoung Yoon, Gyuwan Kim, Gyu-Hwung Cho +1
Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long c…